Biology PhD Scientist Coder for AI Benchmark Tasks

Mercor; San Francisco (CA); On-site; USD 83,000 - 124,000; Part time

Benefits offered by this job

Publications in peer-reviewed journals

Prior scientific software or research‑

Job summary

Mercor is recruiting PhD and Master’s level scientists to author AI evaluation tasks (Sci Code) for a new benchmark in scientific computing. You will craft original, executable research problems that current frontier models cannot solve.

Requirements include a PhD in biology or related fields, demonstrated depth in two biology subdomains, and proficiency in Python or R. Experience with Docker and Git/GitHub is preferred. Duration is 6 weeks, part-time with 20+ hours per week, and immediate start.

Qualifications

• PhD required in biology or closely related field.
• Demonstrated depth in at least two of ecology, biochemistry, genetics.

Responsibilities

• Source own material: a published paper, Kaggle dataset, open-source repo, or designed scenario.
• Write scientific prompts based on the input.
• Build grading criteria that define a correct answer.
• Calibrate against frontier models where strong models fail.

Skills

Python proficiency

Git/GitHub

Scientific computing

Education

PhD in biology or related field

Tools

Python

R

Docker

Git/GitHub

Job description

Mercor is recruiting PhD and Master’s level scientists to author AI evaluation tasks (Sci Code) for a new benchmark in scientific computing. You will craft original, executable research problems that current frontier models cannot solve.

Requirements include a PhD in biology or related fields, demonstrated depth in two biology subdomains, and proficiency in Python or R. Experience with Docker and Git/GitHub is preferred. Duration is 6 weeks, part-time with 20+ hours per week, and immediate start.