Astrophysics Benchmark Designer for AI Research

Mercor; Greater London; Hybrid; GBP 28,000 - 62,000; Part time

Job summary

Mercor is seeking a Computational Astrophysics & Cosmology Expert to design challenging problems for AI benchmarking, using real scientific software and graduate-level workflows.

You will craft problems that test multi-step reasoning, plan experiments, and interpret results with domain tools like Astropy in a Linux environment. Remote collaboration and 15–20 hours weekly are expected.

Qualifications

• Graduate-level training in a relevant STEM field (MS/PhD or equivalent).
• Proven proficiency with scientific software libraries (e.g., Astropy).
• Strong Python skills—writing problem setups, oracle functions, and validators.
• Ability to work independently and refine designs based on feedback.
• Comfortable with Linux/terminal and remote compute sandboxes.
• Available for 15–20 hours per week.

Responsibilities

• Design problems requiring use of specialized scientific software.
• Test problems against AI models and refine difficulty.
• Develop multi-step workflows and evaluation strategies.
• Work with cosmology and astrophysics tools to support benchmarking.

Skills

Python

Linux/Terminal

Code writing

Problem design

Education

PhD or MS in STEM

Tools

Astropy

Job description

Mercor is seeking a Computational Astrophysics & Cosmology Expert to design challenging problems for AI benchmarking, using real scientific software and graduate-level workflows.

You will craft problems that test multi-step reasoning, plan experiments, and interpret results with domain tools like Astropy in a Linux environment. Remote collaboration and 15–20 hours weekly are expected.