Materials Scientist for AI Evaluation

Role Overview

Create original, executable scientific computing problems that help evaluate advanced AI systems. This remote opportunity focuses on materials science tasks with a coding emphasis, drawing on research-grade sources and rigorous evaluation methods.

Key Responsibilities

• Author original, executable research problems designed to challenge frontier AI models.
• Develop tasks using a published paper, Kaggle dataset, open-source repository, or an original scenario you design.
• Write clear scientific prompts based on the selected source material.
• Create grading criteria that define a correct answer.
• Test and calibrate tasks against frontier models, submitting tasks when strong models fail more often than they succeed.

Qualifications

• PhD in materials science, materials engineering, applied physics, chemistry, chemical engineering, or a closely related field. Candidates with a Master''s degree in a relevant scientific discipline may also be considered.
• Demonstrated depth in both semiconductor materials and molecular modeling, with a coding focus.
• 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.
• Peer-reviewed publications and prior scientific software or research engineering experience are preferred.

Work Terms

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

Compensation

$70 per hour.

Application Process

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