Physics Researcher for AI Evaluation

Design original, executable physics research problems that help evaluate the limits of advanced scientific AI systems. This remote, coding-focused opportunity draws on deep expertise across multiple areas of physics to create rigorous tasks that strong frontier models cannot reliably solve. Key Responsibilities

• Author original, executable scientific computing problems grounded in physics research.
• Use source material such as published papers, Kaggle datasets, open-source repositories, or scenarios you create.
• Develop scientific prompts and clear grading criteria that define correct solutions.
• Test and calibrate tasks against frontier models, releasing tasks only when strong models fail more often than they succeed.

• PhD in physics, applied physics, or a closely related field.
• Demonstrated depth in at least two of these coding-focused subdomains: condensed matter, optics, quantum information or computing, computational physics, astrophysics, or particle physics.
• Working proficiency in Python, R, or another relevant scientific-computing language.
• Comfort using Git or GitHub and running code in Docker. Work is completed through a pull-request workflow with automated quality checks.

• Publications in peer-reviewed journals.
• Previous scientific software development or research engineering experience.

• Remote hourly engagement.
• Six-week project with an immediate start date.
• Part-time commitment of 20 or more hours per week.

• $70 per hour.

• Submit your resume and application form.
• Complete a 25-minute conversational interview focused on your background, experience, and motivations.
• Receive an update within a few days regarding next steps and onboarding.