Job Description
Role Overview
We are seeking expert physics researchers to author and verify golden reference solutions for the CritPt benchmark (arXiv: v3) — a frontier research-level physics benchmark. Participants will solve CritPt research-level problems end-to-end, audit solutions from other experts, or adjudicate between parallel solution attempts, producing 100%-human-verified reference data used to evaluate large language models on frontier physics reasoning.
Physics Subdomains Covered
High Energy Physics & Mathematical Physics, Biophysics & Statistical Physics, Condensed Matter & AMO, Gravitation / Cosmology / Astrophysics, Quantum Information, Optical Properties of Materials, Magnetic Materials, Measurements in QM.
Key Responsibilities
- Solve research-level physics challenges end-to-end with verifiable derivations, code, and peer-reviewed references
- Decompose challenges into standalone checkpoint sub-problems t...