Mercor
$80–135/hr
50 people hired
You will contribute to the CritPt frontier research-level physics benchmark by solving, reviewing, and validating advanced physics problems used to evaluate large language models. Depending on expertise, you may work as a Solver, Auditor, or Adjudicator, producing fully human-verified golden reference solutions. The role involves advanced physical reasoning, mathematical derivations, Python-based verification, peer-reviewed research references, solution auditing, and quality adjudication across areas including High Energy Physics, Mathematical Physics, Biophysics, Statistical Physics, Condensed Matter, AMO, Gravitation, Cosmology, Astrophysics, Quantum Information, Optical and Magnetic Materials, and Quantum Measurement.
Research Physics AI Evaluation