Biology PhD — AI Research Benchmark Architect

Obsidian; New York (NY); On-site; USD 83,000 - 138,000; Full time

Job summary

Mercor is hiring PhD and Master’s scientists to author AI evaluation tasks for a new benchmark in scientific computing. You will create original, executable research problems that frontier models struggle with, sourcing material from papers, datasets, or open repositories.

Applicants should show deep expertise in biology and at least two subdomains, plus coding skills (Python/R) and experience with Git/GitHub and Docker workflows for reproducible runs.

Qualifications

• PhD in biology or closely related field.
• Depth in at least two subdomains: ecology, biochemistry, genetics.

Responsibilities

• Source material: papers, datasets, or repositories to design tasks.
• Write scientific prompts based on input.
• Build grading criteria for correct answers.
• Calibrate tasks so frontier models fail more often than succeed.

Skills

Python

R

Scientific computing

Education

PhD in biology

Tools

Git / GitHub

Docker

Job description

Mercor is hiring PhD and Master’s scientists to author AI evaluation tasks for a new benchmark in scientific computing. You will create original, executable research problems that frontier models struggle with, sourcing material from papers, datasets, or open repositories.

Applicants should show deep expertise in biology and at least two subdomains, plus coding skills (Python/R) and experience with Git/GitHub and Docker workflows for reproducible runs.