Scientific Coding Evaluator – STEM Part-time

Scientific Coding Evaluator – STEM

$40-$65 per hour

Hourly contract

Remote

Mercor is seeking PhD holders, doctoral candidates, and exceptional Master's graduates in STEM disciplines with strong scientific programming experience to join a high-impact AI research initiative in partnership with a leading AI lab.

This role involves evaluating and enhancing large language models (LLMs) by applying subject-matter expertise in scientific coding to rigorously assess model performance in STEM-specific programming tasks.

Key Responsibilities

• Evaluate the accuracy, logic, and domain relevance of Python-based code and reasoning generated by LLMs in tasks related to graduate-level science.
• Review outputs across physics, chemistry, biology, and other scientific domains involving numerical methods, data analysis, modeling, and simulation.
• Complete structured evaluations for each task, answering 8–10 rubric questions and providing short written comments explaining each judgment.
• Identify code correctness issues, scientific inaccuracies, and gaps in technical execution.
• Work independently using provided evaluation tools and rubrics in an asynchronous, remote setting.

You're a Strong Fit If You Have:

• A PhD (or are currently a PhD candidate) in Physics, Chemistry, Biology, Engineering, or a related STEM field.
• Strong experience using Python in scientific contexts (e.g. research, modeling, or applied analysis).
• Familiarity with scientific libraries such as NumPy, SciPy, pandas, or similar.
• A strong ability to critically evaluate both scientific reasoning and code implementation.
• Excellent written communication skills and attention to technical detail.
• Comfort working independently and asynchronously in a remote environment.

Role Details

• Part-time (10–20 hours/week) with flexible scheduling.
• 100% remote and asynchronous — work from anywhere, anytime.

Compensation & Legal

• Contractor position via Mercor, paid hourly.
• Competitive rates based on domain expertise, ranging from $40 to $65/hour.
• Weekly payments processed securely through Stripe Connect.

About Mercor

Mercor is a San Francisco-based company specializing in connecting elite professionals with cutting-edge AI initiatives. Our investors include Benchmark, General Catalyst, Adam D'Angelo, Larry Summers, and Jack Dorsey. We help leading AI labs accelerate progress by bringing in top-tier human expertise.

We consider all qualified applicants without regard to legally protected characteristics and provide reasonable accommodations upon request.