Biology AI Evaluation Coder (6-Week Project)

Obsidian; Sydney; On-site; AUD 83,000 - 124,000; Part time

Job summary

Mercor is seeking PhD and Master's level scientists to author AI evaluation tasks for a new benchmark in scientific computing. You will craft original, executable research problems that current frontier models cannot solve and calibrate grading criteria to distinguish correct answers from incorrect ones.

The role emphasizes sourcing materials, writing prompts, and validating tasks through a pull-request workflow with automated quality checks.

Qualifications

• PhD in biology, biological sciences, biochemistry, genetics, ecology, or closely related field.
• Demonstrated depth in at least two subdomains: ecology, biochemistry, genetics.
• Working proficiency in Python, R, or another language for scientific computing.
• Comfortable with Git/GitHub and running code in Docker — PR workflow with automated checks.

Responsibilities

• Source your own material: a published paper, a Kaggle dataset, an open-source repository, or a designed scenario.
• Write scientific prompts based on the input.
• Build grading criteria that define a correct answer.
• Calibrate against frontier models — ensure task fails more often than it succeeds.

Skills

Python

R

Git/GitHub

Docker

Biology

Research

Education

PhD in biology or related field

Tools

Docker

Git

Job description

Mercor is seeking PhD and Master's level scientists to author AI evaluation tasks for a new benchmark in scientific computing. You will craft original, executable research problems that current frontier models cannot solve and calibrate grading criteria to distinguish correct answers from incorrect ones.

The role emphasizes sourcing materials, writing prompts, and validating tasks through a pull-request workflow with automated quality checks.