Remote Materials Science AI Benchmark Scientist (PhD)

1000scholars; United States; Remote; USD 11,572,000 - 14,878,000; Part time

Benefits offered by this job

Weekly payments via Stripe or Wise

Fully remote

Job summary

Mercor is seeking PhD or Master’s scientists to author AI evaluation tasks for a new benchmark in scientific computing. The role is fully remote and contracted as an independent engagement, with a 6-week horizon and a commitment of 20+ hours per week.

You will source materials, design prompts, and establish grading criteria to test frontier models. Payments are weekly via Stripe or Wise, and candidates who require H1-B or STEM OPT are not accommodated.

Qualifications

• PhD in materials-related field.
• Depth in semiconductor materials and molecular modeling.
• Proficient in Python or R.
• Experience with GitHub and Docker workflows.

Responsibilities

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

Skills

Python

R

Education

PhD in Materials Science / related field

Tools

Git / GitHub

Docker

Job description

Mercor is seeking PhD or Master’s scientists to author AI evaluation tasks for a new benchmark in scientific computing. The role is fully remote and contracted as an independent engagement, with a 6-week horizon and a commitment of 20+ hours per week.

You will source materials, design prompts, and establish grading criteria to test frontier models. Payments are weekly via Stripe or Wise, and candidates who require H1-B or STEM OPT are not accommodated.