Materials Scientist: AI Benchmarking & Research Prompts

Obsidian; San Francisco (CA); Remote; USD 8,266,000 - 12,398,000; Full time

Job summary

Mercor is hiring PhD and Masters scientists to author AI evaluation tasks and build a robust benchmark for scientific computing. You will craft original, executable research problems that current frontier models struggle to solve, with focus on semiconductor materials and molecular modeling.

You will source your own material, write prompts, and develop grading criteria while calibrating against failing models.

Qualifications

• PhD in materials science, materials engineering, applied physics, chemistry, chemical engineering, or a closely related field
• Demonstrated depth in both semiconductor materials and molecular modeling
• Working proficiency in Python, R, or another relevant programming language for scientific computing
• Comfortable with Git/GitHub and running code in Docker — authoring runs through a pull-request workflow with automated quality checks

Responsibilities

• Author original, executable research problems that today's frontier models cannot solve
• Build the grading criteria that define a correct answer
• Calibrate against frontier models — a task ships only when strong models fail it more often than they succeed
• Write scientific prompts based on the input
• Source material from papers, datasets, or open-source repositories

Skills

Python

R

Scientific computing

Docker

Git/GitHub

Research design

Education

PhD in materials science or related field

Tools

Docker

GitHub

Job description

Mercor is hiring PhD and Masters scientists to author AI evaluation tasks and build a robust benchmark for scientific computing. You will craft original, executable research problems that current frontier models struggle to solve, with focus on semiconductor materials and molecular modeling.

You will source your own material, write prompts, and develop grading criteria while calibrating against failing models.