Cosmology AI Benchmark Designer

Mercor; New York (NY); Remote; USD 60,000 - 90,000; Full time

Job summary

Mercor seeks a Computational Astrophysics & Cosmology Expert to design graduate-level problems that test AI systems using real scientific workflows. You will craft setups, run simulations, and interpret results, aligning with research-grade standards.

You'\'ll work with Python, Astropy, and other libraries to build challenging tasks, evaluate AI performance, and refine problems through iterative feedback, aiming for robust evaluation in a remote-friendly research environment.

Qualifications

• Graduate-level training in a relevant STEM field (MS, PhD, or equivalent research experience).
• Proven proficiency with at least one scientific software library, shown through research publications or open-source contributions.
• Strong Python skills for problem setups, oracle functions, and solution validators.
• Ability to work independently and refine problem designs based on feedback.
• Comfortable with Linux/terminal environments and remote compute sandboxes.

Responsibilities

• Design graduate-level problems based on real scientific workflows for AI evaluation.
• Test problems against state-of-the-art AI models and refine for target difficulty.
• Build problem setups, oracle functions, and solution validators in Python.
• Apply domain expertise in Astrophysics & Cosmology using Astropy and related tools.

Skills

Python

Astropy

Education

MS/PhD in STEM

Tools

Astropy

Scientific libraries

Job description

Mercor seeks a Computational Astrophysics & Cosmology Expert to design graduate-level problems that test AI systems using real scientific workflows. You will craft setups, run simulations, and interpret results, aligning with research-grade standards.

You'\'ll work with Python, Astropy, and other libraries to build challenging tasks, evaluate AI performance, and refine problems through iterative feedback, aiming for robust evaluation in a remote-friendly research environment.