Precision Talent

Loading

https://howtoacademy.com/: PAID SOCIAL & DIGITAL ADVERTISING MANAGER (U.S.) Contract / Retainer Role

Headquarters: London, United Kingdom

URL: https://howtoacademy.com/

The Opportunity

How To Academy is seeking a highly analytical and strategic Paid Social & Digital Advertising Manager to lead paid social campaign planning and execution across our U.S. events program.

This is a contract/retainer role for a specialist who understands how to scale audience acquisition through paid media while maintaining a premium cultural brand. You will oversee paid social strategy and execution across multiple campaigns and markets, working closely with our U.S. programming and marketing teams to drive ticket sales, audience growth, and brand awareness.

We are looking for someone who combines agency-level rigour with entrepreneurial agility: data-driven, highly responsive, and capable of managing multiple campaigns across different cities and talent profiles simultaneously.

Key Responsibilities

Paid Social Strategy & Planning

  • Develop and execute paid social strategies across Meta (Facebook & Instagram) and other relevant platforms (e.g. YouTube, TikTok, Pinterest where appropriate).
  • Build full-funnel campaign structures designed reminding conversion across awareness, consideration, and ticket-purchase stages.
  • Align paid social activity with broader marketing efforts including email, partnerships, PR, and organic social.
  • Advise on budget allocation by market, talent profile, and sales trajectory.
  • Identify audience growth opportunities across key U.S. cities and touring markets.

 Campaign Execution & Management

  • Lead day-to-day management of paid social campaigns across multiple live events.
  • Create and test ad variations (copy, creative, audience targeting, placements).
  • Monitor performance daily and optimize for conversion, cost efficiency, and scale.
  • Manage retargeting, lookalike audiences, and pixel tracking to improve performance.
  • Ensure all campaigns are aligned with ticket on-sale timelines and sales pacing.

 Data, Insights & Reporting

  • Conduct audits of campaign performance and recommend improvements.
  • Provide clear, actionable weekly reporting on:
    • Spend vs revenue
    • Cost per conversion
    • Audience performance
    • Market comparisons
  • Use data to inform creative direction, targeting strategy, and budget decisions.
  • Advise on website and funnel optimization to ensure campaigns are “ad-ready” and conversion-focused.

 Collaboration & Advisory

  • Work closely with U.S. leadership, producers, and designers to align marketing with commercial goals.
  • Advise on creative best practices for paid social assets.
  • Recommend testing strategies and new platform opportunities.
  • Provide occasional strategic audits or campaign deep dives as required.

Who You Are

You are a paid social specialist with strong strategic instincts and deep platform knowledge. You understand performance marketing within a premium brand context and can balance data, creative, and audience insight to drive results.

Essential Skills & Experience

  • Proven experience managing paid social campaigns with measurable ROI.
  • Strong expertise in Meta Ads Manager and conversion-driven campaign structures.
  • Experience scaling campaigns across multiple markets simultaneously.
  • Highly analytical with strong reporting and optimization skills.
  • Ability to interpret performance data and translate into actionable strategy.
  • Excellent communication and responsiveness in a remote working environment.
  • Experience working independently on a contract/retainer basis.

 Nice to Have

  • Experience marketing live events, tours, cultural programming, or ticketed experiences.
  • Familiarity with U.S. cultural, literary, or media audiences.
  • Experience integrating paid social with email and broader digital marketing.
  • Understanding of premium brand positioning and audience targeting.

 Scope & Structure

  • Contract/retainer role (hours and scope scalable based on campaign volume).
  • Fully remote.
  • Monthly retainer or project-based structure depending on experience and availability.
  • Immediate start preferred as U.S. programming continues to expand.

 Reporting Line

This role will report into the Head of Marketing, Fane Group, and work closely with How To Academy’s U.S. leadership, producers, and creative teams.

How to Apply

Please send a short introduction, relevant experience, and examples of campaigns you’ve managed (particularly conversion-driven campaigns) to: jobs@howtoacademy.com

To apply: https://weworkremotely.com/remote-jobs/https-howtoacademy-com-paid-social-digital-advertising-manager-u-s-contract-retainer-role

Maverick Trading: Forex & Crypto Trader – Remote

Headquarters: Salt Lake City, UT, USA

URL: http://mavericktrading.com

Trade Forex & Crypto with firm capital — without passing a challenge or risking your own money.

Maverick Currencies is not your typical prop trading firm. We don’t run “challenges” or profit from failed traders—we profit only when you profit. That means our incentives are fully aligned with your success.

For over 25 years, we’ve funded traders around the world — from experienced professionals to motivated individuals looking to build a trading career. Whether you’re ready for capital now or want structured training to get there, we provide the support, mentorship, and funding to help you grow.


Why Join Us

  • Profit splits up to 90% — keep the majority of what you earn

  • Capital scales with performance — grow your account as you grow your edge

  • We fund experienced traders — step in and trade firm capital

  • We train and fund new traders — no challenges, just structured development

  • Start part-time, transition to full-time if you choose

  • Fully remote, async environment — trade on your schedule

  • 25+ year track record — one of the most established prop firms in the U.S.


What This Role Is (and Isn’t)

  • Trade firm capital and earn a profit split (this is not a salaried position)

  • No challenge fees or pay-to-play model

  • Performance-based growth path — your results determine your progression

  • Structured support, coaching, and community


The Role

  • Trade Forex and/or Crypto markets using firm capital

  • Apply disciplined risk management and a structured trading approach

  • Work independently while engaging with a global network of traders

  • Continuously improve your performance with coaching and feedback


Who This Is For

  • Traders with Forex or Crypto experience looking for capital and structure

  • Individuals serious about developing a long-term trading skillset

  • Self-directed professionals who value flexibility and autonomy

  • People comfortable working in a performance-based environment


This Role Is NOT For

  • Those looking for a guaranteed salary or traditional employment model

  • Anyone expecting quick or passive income

  • Individuals unwilling to follow a structured development process


Our Culture

We’re a fully remote team spread across time zones. Traders here thrive on autonomy, flexibility, and async collaboration. No commutes, no constant meetings — just the freedom to trade your edge while being supported by a seasoned community.

At Maverick, many traders start part-time while working another job, then transition into full-time trading as their performance grows. We’re focused on long-term development, not short-term hype.

To apply: https://weworkremotely.com/remote-jobs/maverick-trading-forex-crypto-trader-remote-1

Senex: Full Stack Developer (PHP, React, MySQL)

Headquarters: Bari, Italia

Descrizione dell’aziendaVuoi lavorare su un prodotto che migliora davvero la vita delle persone?In Ninacare stiamo costruendo il primo HR-tech italiano dedicato al settore sanitario, aiutando migliaia di professionisti sanitari a trovare il lavoro giusto e le strutture sanitarie a trovare professionisti qualificati.Con oltre 16.000 professionisti iscritti, un’integrazione diretta con Indeed ed altre job platform, e un motore di matching basato su AI, stiamo rivoluzionando un settore ancora troppo legato ai vecchi metodi di reclutamento.Siamo in forte crescita e cerchiamo un* Full Stack Developer pronto a imparare, contribuire e crescere con noi.Descrizione del lavoroCosa faraiLavorerai a stretto contatto con la nostra CPO ed il nostro Senior software engineer e ti occuperai di:Sviluppare e mantenere funzionalità full stack usando PHP (Laravel), React, MySQL e Inertia.jsCollaborare con il team di prodotto per creare interfacce moderne, responsive e performantiOttimizzare il codice per garantire scalabilità, velocità e stabilitàPartecipare a tutte le fasi del ciclo di sviluppo: idea, design, sviluppo, testing, rilascioMantenere alta la qualità del codice e contribuire all’automazione dei processiIl nostro tech stack:JS/TS, React, Tailwind, Inertia.jsPHP, Laravel, MySQLAWS, Terraform, Docker, GitHubQualificheChi cerchiamoAlmeno 2 anni di esperienza come sviluppatore full stackOttima padronanza di PHP (Laravel), Javascript, React, MySQLCapacità di scrivere codice pulito, scalabile e ben documentatoAttitudine al problem solving, curiosità e voglia di crescereEsperienza in ambienti Agile/ScrumMentalità proattiva, spirito di squadra e buone doti relazionaliCostituiscono un plusEsperienza di studio o lavoro all’esteroOttima conoscenza dell’inglese (o di un’altra lingua)Interesse per AI, Machine Learning e automazioni avanzateUlteriori informazioniCosa offriamoLavoro 100% remoto (con base a Bari ma team distribuito)Ambiente giovane, dinamico e data-drivenPossibilità concreta di crescita e formazione internaAccesso a progetti innovativi legati ad AI, CV parsing, automazioni, conversational agentsStock options e bonus legati agli obiettiviRAL tra €30.000 e €38.000, commisurata all’esperienza + bonus performance

To apply: https://weworkremotely.com/remote-jobs/senex-full-stack-developer-php-react-mysql

Mrp My Recruitment Partners: German speaking Full Stack Developer mit Erfahrung in Shopware 6 (all genders) – 100% remote

Headquarters: Paderborn, NW, 33100 Germany

Job descriptionDu bist nicht der typische Full Stack Developer? Wir suchen einen Developer, der transparente Kommunikation, sauberes Coding und qualitativ hochwertige Arbeit nicht nur als Floskel verwendet.Das „montagmorgens“-Gefühl gibt es bei uns nicht:Bei uns darfst Du so sein, wie Du wirklich bist! Koro, Zalando, FC Moto, Wöhrl – Abwechslungsreiche Aufgaben und ProjekteWir leben Feedback und fördern dies!Von Bahncard bis WalkingPad – wir lieben individuelle Ziel- & GehaltssystemeWeiterbildungsmaßnahmen gehören für uns zum AlltagDeine Wunsch-HardwareModerne Büros und die Möglichkeit 100 % remote zu arbeiten80–90 aktive Kunden, die man durch Werbung auf ProSieben oder Höhle der Löwen kenntTeamspirit wird bei uns großgeschrieben – Nerfgun und lustige Memes gehören für uns dazu!minimaler bis starker Kundenkontakt – du entscheidestTech Stack: https://stackshare.io/companies/8mylez-gmbhDiese Aufgaben warten auf DichEin variabler Mix aus Frontend und Backend – HTML, CSS & JavaScript (Vue.Js, React), PHP (Symfony)Konfiguration & Weiterentwicklung von einzigartigen OnlineshopsImplementierung & Umsetzung von Layouts und vorhandenen DesignsUmsetzung komplexer Funktionen und ErweiterungenEntwicklung von innovativen Ideen für den E-CommerceErkunden und Lernen von modernen und neuen WebtechnologienDas bringst Du mitMind. 2 Jahre Erfahrung in Shopware 6Gute Kenntnisse in PHP, insbesondere SymfonyErfahrung mit JavaScript-Frameworks wie Vue.js oder ReactSicherer Umgang mit Git und gängigen Entwicklungs-WorkflowsSpaß, Leidenschaft und persönliches Interesse am ProgrammierenVerantwortungs- und QualitätsbewusstseinLösungsorientierte und selbstständige ArbeitsweiseÜber unsAls ambitionierte E-Commerce-Agentur, mit rund 35 Menschen an Bord, gestalten wir das digitale Einkaufen von morgen und betreuen marktführende Onlineshops. Werde jetzt Teil und hilf mit, das Internet jeden Tag schöner, besser und schneller zu machen.Dir fehlt etwas in unserer Liste?Dann lass es uns in Deinem Anschreiben wissen.All done!Your application has been successfully submitted!Other jobs

To apply: https://weworkremotely.com/remote-jobs/mrp-my-recruitment-partners-german-speaking-full-stack-developer-mit-erfahrung-in-shopware-6-all

Java & React: Full Stack Developer Java & React (100% remote)

Headquarters: Remoto

Descripción del puesto / Funciones¿Eres un/a desarrollador/a Full Stack con pasión por la innovación y la escalabilidad? ¡Esta es tu oportunidad! Estamos buscando un perfil versátil para unirse a un proyecto internacional del sector eCommerce, desarrollando soluciones digitales de alto impacto.Requisitos mínimos+3 años de experiencia profesional como desarrollador/a full stack.Desarrollar y mantener aplicaciones full stack escalables y de alto rendimiento.Construir servicios backend robustos usando Java y Spring Boot.Diseñar interfaces dinámicas y responsivas con React y Redux.Utilizar Docker para contenerización y desplegar en entornos AWS.Colaborar con desarrolladores, diseñadores y otros stakeholders en un entorno ágil.Participar en ceremonias Scrum: planning, dailies, retrospectives.Asegurar la calidad del código mediante unit testing y code reviews.Dominio de Java, Spring Boot, React y Redux.Experiencia con Docker y despliegue en AWS.Buenas habilidades de comunicación y trabajo en equipo.Experiencia previa en entornos organizativos complejos o multinacionales.Inglés fluido (imprescindible).Requisitos valorablesConocimiento de Azure DevOps (CI/CD, gestión de proyectos).Experiencia previa en plataformas eCommerce o de cara al cliente.Sensibilidad por principios de UX/UI y accesibilidad web.UbicaciónRemoto 100%¿Quiénes somos? Pasiona Consulting es una consultora tecnológica, partner de Microsoft, dedicada al diseño, desarrollo e implementación de aplicaciones de software a medida para clientes de múltiples sectores.

To apply: https://weworkremotely.com/remote-jobs/java-react-full-stack-developer-java-react-100-remote

Bold & Epic Craft Llc: Full Stack Developer (PHP, Laravel, WordPress & JavaScript)

Headquarters: Georgia (remote)

Get to know us:BOLD & EPIC Craft – the new work network challenges the status quo of the working world. We believe in our colleagues. And that only happy people do great work. We don’t care when and where. We want to create a place where everyone enjoys creating.Culture:At BOLD & EPIC Craft our success is powered by people. Our culture is what makes BOLD & EPIC Craft a rewarding place to work. We look at each and every person as a vital member of the team. BOLD & EPIC Craft is a space where people can find themselves represented and reflected, and where they understand that all people are treated with respect and dignity.There’s a potential opportunity to work for a German design and web development agency specialising in creating impressive digital experiences that inspire clients and drive their business success.We are in search of a proactive developer for ongoing support and feature development of a career platform integrated with Workday for a large German company (over 1,000 open positions). You will be the sole developer, working directly with the client via an Asana board to discuss requirements, and solve issues. In this role, you’ll have the freedom to propose new ideas, think creatively, and focus on solution-oriented development. Strong communication and initiative are key, as you’ll work closely with the client to ensure continuous improvement and adaptation to their needs.Working details: 40h hours per week, fully remotelyThe hiring process:15-Minute Interview with the Georgian HR Manager: Initial conversation to discuss your background, qualifications, and alignment with the company culture.30-Minute Chemistry Meeting with the German CEO: An informal meeting focused on building rapport, understanding the company’s vision, and discussing mutual expectations.2 Days to Reflect: Time given to consider the opportunity, assess alignment with your career goals, and prepare for the technical discussion.90-Minute Technical Discussion: A detailed technical interview to evaluate your skills, problem-solving approach, and ability to work with their tech stack.Decision within 5 Days: Final decision communicated within five days after the technical discussion.Start : As soon as possibleFull Stack Development: Responsible for implementing and optimizing web solutions based on PHP, Laravel, and WordPress.Frontend Development: Develop and maintain responsive, interactive user interfaces with modern JavaScript frameworks and Tailwind CSS.Backend Development: Integrate external APIs (REST & SOAP) and develop server-side logic, especially in Laravel and WordPress.Job Scheduling & Queue Management: Manage Laravel jobs and queues and integrate APIs such as the Workday API.Testing & Debugging: Conduct unit tests, code reviews, and debugging to ensure high code quality.Performance Optimization: Optimize both frontend and backend components for improved load times, SEO, and user experience.Profile:Full Stack Development Experience: At least 3 years of experience with PHP (Laravel, WordPress) and JavaScript (ES6+), including API integration and database optimization.Frontend Competence: Strong knowledge of HTML5, CSS3, JavaScript (React or Vanilla JS), along with performance optimization and accessibility.Backend Experience: In-depth understanding of working with Laravel, WordPress, and MySQL databases.Testing & Debugging: Experience with unit tests (PHPUnit, Mockery) and debugging complex web applications.Tools & DevOps: Familiarity with Docker, Git, Composer, and CI/CD pipelines.Skills:Experience with SOAP-based enterprise APIs like Workday.Knowledge of configuring Docker and CI/CD pipelines.Experience with modern JavaScript frameworks such as Vue.js.Basic knowledge of Sentry and setting up release tags.Tech Stack:Frontend:JavaScript (ES6+): Modern JavaScript, including DOM manipulation, event handling, and API integration (e.g., Fetch API, AJAX).React or Vanilla JS: Using React or native JavaScript to develop dynamic user interfaces.HTML5 & CSS3: Structuring, semantics, and responsive design with a particular focus on accessibility.Tailwind CSS & SASS: For efficient, modular, and scalable CSS solutions.SEO & Performance Optimization: Focus on SEO best practices, page speed optimizations (e.g., TTFB, layout shift).Backend:PHP 8.x: Modern PHP development with a focus on performance and security.Laravel 8.x+: Scalable web applications, API integrations, and queue management.WordPress: Development and maintenance of custom plugins and themes, with a deep understanding of the WordPress core.MySQL: Optimization and management of relational databases, migrations, and complex queries.Tools & DevOps:Docker: Local development environment and application containerization.Git & GitHub: Version control and CI/CD pipelines.Composer: Dependency management for PHP projects.WP CLI: Automation and maintenance of WordPress instances.PHPUnit & Mockery: Unit tests to ensure code quality.Sentry: Real-time error monitoring and logging.We’d be great together if:                                           Working in a startup environment excites you – yes, we get the memes and are over- achievers;You have a structure and performance-oriented mindset;               You’re attentive to details others might miss;                  Communication and problem solving bring you joy;                                      You are fluent in English;If the feeling is mutual, we offer:Competitive salary Premium Health Insurance package;Fitpass;Language Courses;Organized events and outdoor activities;Work-life balance – 28 paid holidays per year;Career growth opportunities;Working from home.   

To apply: https://weworkremotely.com/remote-jobs/bold-epic-craft-llc-full-stack-developer-php-laravel-wordpress-javascript

Jump: Join the Jump Product & Design Talent Pool

Headquarters: Los Angeles, California, USA

Thanks for your interest in learning more about Jump! We are always on the lookout for talented product managers and product designers to join our growing team.  So drop us a line if you’re interested in being added to our talent pool. Read more about what we’re building and how to stay in touch below.Jump is the only end-to-end fan experience platform built for sports teams and venues, breaking the mold for what fans can expect at live events. Jump’s enterprise software enables sports teams and venues to unlock the massive opportunities that come from real relationships with their fans, rethinking the traditional model that hasn’t put the fan experience first.Founded in 2021 by Marc Lore, Alex Rodriguez, and Jordy Leiser and backed by top venture firms including Forerunner Ventures, Will Ventures, Mastry Ventures, Courtside Ventures, and more, we’re just getting started! We are a remote first team that grounds our actions and decisions in our core values — begin with trust, bring our all, and blaze a trail. Living our values means that we always assume positive intent, show up with authenticity and empathy, and push the limit of what is possible with our collective creativity.As a member of the Product & Design team, you’ll have a strong voice in product strategy and defining the future of live event experiences. We experiment, move fast, fail quickly, and apply new learnings as we try new ideas. You will work closely with passionate leaders, engineers, and other product managers & designers to build transformational experiences for fans and teams. We look for people with the following traits:A strong desire to learn. You are curious and willing to dive deep to become a subject matter expert in our domainTenacity. You enjoy working on challenges that others can’t or don’t want to tackle and you aren’t afraid of failing fast in order to find better solutions.Passion. You love using your technical skills to build products that solve real problems. You hold yourself to a high standard and help to elevate others as well.Empathy. You thrive in an environment where everyone can truly be themselves. You understand that our differing life experiences influence who we are and how we show up, and these diverse perspectives enrich both our team and our product.Customer-centric mindset. You can understand the problem to be solved and who we are solving it for.If this sounds aligned with your skills and interests, drop us your resume and we’ll reach out if there’s a role that might align with our team’s needs in the future.

To apply: https://weworkremotely.com/remote-jobs/jump-join-the-jump-product-design-talent-pool

Evaluating the ethics of autonomous systems

Artificial intelligence is increasingly being used to help optimize decision-making in high-stakes settings. For instance, an autonomous system can identify a power distribution strategy that minimizes costs while keeping voltages stable.

But while these AI-driven outputs may be technically optimal, are they fair? What if a low-cost power distribution strategy leaves disadvantaged neighborhoods more vulnerable to outages than higher-income areas?

To help stakeholders quickly pinpoint potential ethical dilemmas before deployment, MIT researchers developed an automated evaluation method that balances the interplay between measurable outcomes, like cost or reliability, and qualitative or subjective values, such as fairness.   

The system separates objective evaluations from user-defined human values, using a large language model (LLM) as a proxy for humans to capture and incorporate stakeholder preferences. 

The adaptive framework selects the best scenarios for further evaluation, streamlining a process that typically requires costly and time-consuming manual effort. These test cases can show situations where autonomous systems align well with human values, as well as scenarios that unexpectedly fall short of ethical criteria.

“We can insert a lot of rules and guardrails into AI systems, but those safeguards can only prevent the things we can imagine happening. It is not enough to say, ‘Let’s just use AI because it has been trained on this information.’ We wanted to develop a more systematic way to discover the unknown unknowns and have a way to predict them before anything bad happens,” says senior author Chuchu Fan, an associate professor in the MIT Department of Aeronautics and Astronautics (AeroAstro) and a principal investigator in the MIT Laboratory for Information and Decision Systems (LIDS).

Fan is joined on the paper by lead author Anjali Parashar, a mechanical engineering graduate student; Yingke Li, an AeroAstro postdoc; and others at MIT and Saab. The research will be presented at the International Conference on Learning Representations.

Evaluating ethics

In a large system like a power grid, evaluating the ethical alignment of an AI model’s recommendations in a way that considers all objectives is especially difficult.

Most testing frameworks rely on pre-collected data, but labeled data on subjective ethical criteria are often hard to come by. In addition, because ethical values and AI systems are both constantly evolving, static evaluation methods based on written codes or regulatory documents require frequent updates.

Fan and her team approached this problem from a different perspective. Drawing on their prior work evaluating robotic systems, they developed an experimental design framework to identify the most informative scenarios, which human stakeholders would then evaluate more closely.

Their two-part system, called Scalable Experimental Design for System-level Ethical Testing (SEED-SET), incorporates quantitative metrics and ethical criteria. It can identify scenarios that effectively meet measurable requirements and align well with human values, and vice versa.   

“We don’t want to spend all our resources on random evaluations. So, it is very important to guide the framework toward the test cases we care the most about,” Li says.

Importantly, SEED-SET does not need pre-existing evaluation data, and it adapts to multiple objectives.

For instance, a power grid may have several user groups, including a large rural community and a data center. While both groups may want low-cost and reliable power, each group’s priority from an ethical perspective may vary widely.

These ethical criteria may not be well-specified, so they can’t be measured analytically.

The power grid operator wants to find the most cost-effective strategy that best meets the subjective ethical preferences of all stakeholders.

SEED-SET tackles this challenge by splitting the problem into two, following a hierarchical structure. An objective model considers how the system performs on tangible metrics like cost. Then a subjective model that considers stakeholder judgements, like perceived fairness, builds on the objective evaluation.

“The objective part of our approach is tied to the AI system, while the subjective part is tied to the users who are evaluating it. By decomposing the preferences in a hierarchical fashion, we can generate the desired scenarios with fewer evaluations,” Parashar says.

Encoding subjectivity

To perform the subjective assessment, the system uses an LLM as a proxy for human evaluators. The researchers encode the preferences of each user group into a natural language prompt for the model.

The LLM uses these instructions to compare two scenarios, selecting the preferred design based on the ethical criteria.

“After seeing hundreds or thousands of scenarios, a human evaluator can suffer from fatigue and become inconsistent in their evaluations, so we use an LLM-based strategy instead,” Parashar explains.

SEED-SET uses the selected scenario to simulate the overall system (in this case, a power distribution strategy). These simulation results guide its search for the next best candidate scenario to test.

In the end, SEED-SET intelligently selects the most representative scenarios that either meet or are not aligned with objective metrics and ethical criteria. In this way, users can analyze the performance of the AI system and adjust its strategy.

For instance, SEED-SET can pinpoint cases of power distribution that prioritize higher-income areas during periods of peak demand, leaving underprivileged neighborhoods more prone to outages.

To test SEED-SET, the researchers evaluated realistic autonomous systems, like an AI-driven power grid and an urban traffic routing system. They measured how well the generated scenarios aligned with ethical criteria.

The system generated more than twice as many optimal test cases as the baseline strategies in the same amount of time, while uncovering many scenarios other approaches overlooked.

“As we shifted the user preferences, the set of scenarios SEED-SET generated changed drastically. This tells us the evaluation strategy responds well to the preferences of the user,” Parashar says.

To measure how useful SEED-SET would be in practice, the researchers will need to conduct a user study to see if the scenarios it generates help with real decision-making.

In addition to running such a study, the researchers plan to explore the use of more efficient models that can scale up to larger problems with more criteria, such as evaluating LLM decision-making.

This research was funded, in part, by the U.S. Defense Advanced Research Projects Agency.

Preview tool helps makers visualize 3D-printed objects

Designers, makers, and others often use 3D printing to rapidly prototype a range of functional objects, from movie props to medical devices. Accurate print previews are essential so users know a fabricated object will perform as expected.

But previews generated by most 3D-printing software focus on function rather than aesthetics. A printed object may end up with a different color, texture, or shading than the user expected, resulting in multiple reprints that waste time, effort, and material.

To help users envision how a fabricated object will look, researchers from MIT and elsewhere developed an easy-to-use preview tool that puts appearance first.

Users upload a screenshot of the object from their 3D-printing software, along with a single image of the print material. From these inputs, the system automatically generates a rendering of how the fabricated object is likely to look.

The artificial intelligence-powered system, called VisiPrint, is designed to work with a range of 3D-printing software and can handle any material example. It considers not only the color of the material, but also gloss, translucency, and how nuances of the fabrication process affect the object’s appearance.

Such aesthetics-focused previews could be especially useful in areas like dentistry, by helping clinicians ensure temporary crowns and bridges match the appearance of a patient’s teeth, or in architecture, to aid designers in assessing the visual impact of models.

“3D printing can be a very wasteful process. Some studies estimate that as much as a third of the material used goes straight to the landfill, often from prototypes the user ends of discarding. To make 3D printing more sustainable, we want to reduce the number of tries it takes to get the prototype you want. The user shouldn’t have to try out every printing material they have before they settle on a design,” says Maxine Perroni-Scharf, an electrical engineering and computer science (EECS) graduate student and lead author of a paper on VisiPrint.

She is joined on the paper by Faraz Faruqi, a fellow EECS graduate student; Raul Hernandez, an MIT undergraduate; SooYeon Ahn, a graduate student at the Gwangju Institute of Science and Technology; Szymon Rusinkiewicz, a professor of computer science at Princeton University; William Freeman, the Thomas and Gerd Perkins Professor of EECS at MIT and a member of the Computer Science and Artificial Intelligence Laboratory (CSAIL); and senior author Stefanie Mueller, an associate professor of EECS and Mechanical Engineering at MIT, and a member of CSAIL. The research will be presented at the ACM CHI Conference on Human Factors in Computing Systems.

Accurate aesthetics

The researchers focused on fused deposition modeling (FDM), the most common type of 3D printing. In FDM, print material filament is melted and then squirted through a nozzle to fabricate an object one layer at a time.

Generating accurate aesthetic previews is challenging because the melting and extrusion process can change the appearance of a material, as can the height of each deposited layer and the path the nozzle follows during fabrication.

VisiPrint uses two AI models that work together to overcome those challenges.

The VisiPrint preview is based on two inputs: a screenshot of the digital design from a user’s 3D-printing software (called “slicer” software), and an image of the print material, which can be taken from an online source or captured from a printed sample.

From these inputs, a computer vision model extracts features from the material sample that are important for the object’s appearance.

It feeds those features to a generative AI model that computes the geometry and structure of the object, while incorporating the so-called “slicing” pattern the nozzle will follow as it extrudes each layer.

The key to the researchers’ approach is a special conditioning method. This involves carefully adjusting the inner workings of the model to guide it, so it follows the slicing pattern and obeys the constraints of the 3D-printing process.

Their conditioning method utilizes a depth map that preserves the shape and shading of the object, along with a map of the edges that reflects the internal contours and structural boundaries.

“If you don’t have the right balance of these two things, you could use up with bad geometry or an incorrect slicing pattern. We had to be careful to combine them in the right way,” Perroni-Scharf says.

A user-focused system

The team also produced an easy-to-use interface where one can upload the required images and evaluate the preview.

The VisiPrint interface enables more advanced makers to adjust multiple settings, such as the influence of certain colors on the final appearance.

In the end, the aesthetic preview is intended to complement the functional preview generated by slicer software, since VisiPrint does not estimate printability, mechanical feasibility, or likelihood of failure.

To evaluate VisiPrint, the researchers conducted a user study that asked participants to compare the system to other approaches. Nearly all participants said it provided better overall appearance as well as more textural similarity with printed objects.

In addition, the VisiPrint preview process took about a minute on average, which was more than twice as fast as any competing method.

“VisiPrint really shined when compared to other AI interfaces. If you give a more general AI model the same screenshots, it might randomly change the shape or use the wrong slicing pattern because it had no direct conditioning,” she says.

In the future, the researchers want to address artifacts that can occur when model previews have extremely fine details. They also want to add features that allow users to optimize parts of the printing process beyond color of the material.

“It is important to think about the way that we fabricate objects. We need to continue striving to develop methods that reduce waste. To that end, this marriage of AI with the physical making process is an exciting area of future work,” Perroni-Scharf says.

“‘What you see is what you get’ has been the main thing that made desktop publishing ‘happen’ in the 1980s, as it allowed users to get what they wanted at first try. It is time to get WYSIWYG for 3D printing as well. VisiPrint is a great step in this direction,” says Patrick Baudisch, a professor of computer science at the Hasso Plattner Institute, who was not involved with this work.

This research was funded, in part, by an MIT Morningside Academy for Design Fellowship and an MIT MathWorks Fellowship.

MIT researchers use AI to uncover atomic defects in materials

In biology, defects are generally bad. But in materials science, defects can be intentionally tuned to give materials useful new properties. Today, atomic-scale defects are carefully introduced during the manufacturing process of products like steel, semiconductors, and solar cells to help improve strength, control electrical conductivity, optimize performance, and more.

But even as defects have become a powerful tool, accurately measuring different types of defects and their concentrations in finished products has been challenging, especially without cutting open or damaging the final material. Without knowing what defects are in their materials, engineers risk making products that perform poorly or have unintended properties.

Now, MIT researchers have built an AI model capable of classifying and quantifying certain defects using data from a noninvasive neutron-scattering technique. The model, which was trained on 2,000 different semiconductor materials, can detect up to six kinds of point defects in a material simultaneously, something that would be impossible using conventional techniques alone.

“Existing techniques can’t accurately characterize defects in a universal and quantitative way without destroying the material,” says lead author Mouyang Cheng, a PhD candidate in the Department of Materials Science and Engineering. “For conventional techniques without machine learning, detecting six different defects is unthinkable. It’s something you can’t do any other way.”

The researchers say the model is a step toward harnessing defects more precisely in products like semiconductors, microelectronics, solar cells, and battery materials.

“Right now, detecting defects is like the saying about seeing an elephant: Each technique can only see part of it,” says senior author and associate professor of nuclear science and engineering Mingda Li. “Some see the nose, others the trunk or ears. But it is extremely hard to see the full elephant. We need better ways of getting the full picture of defects, because we have to understand them to make materials more useful.”

Joining Cheng and Li on the paper are postdoc Chu-Liang Fu, undergraduate researcher Bowen Yu, master’s student Eunbi Rha, PhD student Abhijatmedhi Chotrattanapituk ’21, and Oak Ridge National Laboratory staff members Douglas L Abernathy PhD ’93 and Yongqiang Cheng. The paper appears today in the journal Matter.

Detecting defects

Manufacturers have gotten good at tuning defects in their materials, but measuring precise quantities of defects in finished products is still largely a guessing game.

“Engineers have many ways to introduce defects, like through doping, but they still struggle with basic questions like what kind of defect they’ve created and in what concentration,” Fu says. “Sometimes they also have unwanted defects, like oxidation. They don’t always know if they introduced some unwanted defects or impurity during synthesis. It’s a longstanding challenge.”

The result is that there are often multiple defects in each material. Unfortunately, each method for understanding defects has its limits. Techniques like X-ray diffraction and positron annihilation characterize only some types of defects. Raman spectroscopy can discern the type of defect but can’t directly infer the concentration. Another technique known as transmission electron microscope requires people to cut thin slices of samples for scanning.

In a few previous papers, Li and collaborators applied machine learning to experimental spectroscopy data to characterize crystalline materials. For the new paper, they wanted to apply that technique to defects.

For their experiment, the researchers built a computational database of 2,000 semiconductor materials. They made sample pairs of each material, with one doped for defects and one left without defects, then used a neutron-scattering technique that measures the different vibrational frequencies of atoms in solid materials. They trained a machine-learning model on the results.

“That built a foundational model that covers 56 elements in the periodic table,” Cheng says. “The model leverages the multihead attention mechanism, just like what ChatGPT is using. It similarly extracts the difference in the data between materials with and without defects and outputs a prediction of what dopants were used and in what concentrations.”

The researchers fine-tuned their model, verified it on experimental data, and showed it could measure defect concentrations in an alloy commonly used in electronics and in a separate superconductor material.

The researchers also doped the materials multiple times to introduce multiple point defects and test the limits of the model, ultimately finding it can make predictions about up to six defects in materials simultaneously, with defect concentrations as low as 0.2 percent.

“We were really surprised it worked that well,” Cheng says. “It’s very challenging to decode the mixed signals from two different types of defects — let alone six.”

A model approach

Typically, manufacturers of things like semiconductors run invasive tests on a small percentage of products as they come off the manufacturing line, a slow process that limits their ability to detect every defect.

“Right now, people largely estimate the quantities of defects in their materials,” Yu says. “It is a painstaking experience to check the estimates by using each individual technique, which only offers local information in a single grain anyway. It creates misunderstandings about what defects people think they have in their material.”

The results were exciting for the researchers, but they note their technique measuring the vibrational frequencies with neutrons would be difficult for companies to quickly deploy in their own quality-control processes.

“This method is very powerful, but its availability is limited,” Rha says. “Vibrational spectra is a simple idea, but in certain setups it’s very complicated. There are some simpler experimental setups based on other approaches, like Raman spectroscopy, that could be more quickly adopted.”

Li says companies have already expressed interest in the approach and asked when it will work with Raman spectroscopy, a widely used technique that measures the scattering of light. Li says the researchers’ next step is training a similar model based on Raman spectroscopy data. They also plan to expand their approach to detect features that are larger than point defects, like grains and dislocations.

For now, though, the researchers believe their study demonstrates the inherent advantage of AI techniques for interpreting defect data.

“To the human eye, these defect signals would look essentially the same,” Li says. “But the pattern recognition of AI is good enough to discern different signals and get to the ground truth. Defects are this double-edged sword. There are many good defects, but if there are too many, performance can degrade. This opens up a new paradigm in defect science.”

The work was supported, in part, by the Department of Energy and the National Science Foundation.