Job Description

Mercor is hiring PhD and Master's scientists to author AI evaluation tasks (Sci Code)

n

Mercor is partnering with leading AI labs on a recent benchmark for scientific computing. You will author original, executable research problems that today's frontier models cannot solve.

n

Domains — depth required in at least two subdomains (with a coding focus)

n

n
- Biology — ecology, biochemistry, genetics
n

n

What you'll do

n

n
- Source your own material: a published paper, a Kaggle dataset, an open-source repository, or a scenario you design
n
- Write scientific prompts based on the input
n
- Build the grading criteria that define a correct answer
n
- Calibrate against frontier models — a task ships only when strong models fail it more often than they succeed
n

n

Required

n

n
- PhD in biology, biological sciences, biochemistry, genetics, ecology, or a closely related field
n




- Demonstrated depth in at least two of the following subdomains: ecology, biochemistry, genetics
n
- Working proficiency in Python, R, or another relevant programming language for scientific computing
n
- Comfortable with Git/GitHub and running code in Docker — authoring runs through a pull-request workflow with automated quality checks
n

n

Preferred

n

n
- Publications in peer-reviewed journals
n
- Prior scientific software or research engineering experience
n

n

Engagement

n

n
- Duration: 6 weeks
n
- Commitment: part-time, 20+ hours per week
n
- Start date: immediate
n

n

Process

n

n
- A 25-minute conversational interview covering your background, experience, and motivations
n
- Follow up within a few days with next steps and onboarding
n

n

#J-18808-Ljbffr

📌 Biology PhD - Scientific Coder (New South Wales)
🏢 Obsidian
📍 New South Wales