Physics Domain Expert
$90–$140 / hourRemote · US
We are looking for senior physicists to improve how frontier AI models reason about real physics research.
- Physics
- Research
- Expert Review
Help define how frontier AI models reason about physics.
1. Overview
We are looking for senior physicists to improve how frontier AI models reason about real physics research.
Your scientific judgment is the substance of this role. You will review the quality of physics reasoning tasks and model outputs, write the problem specifications and reference solutions that define what "correct" looks like, and design benchmarks that show whether a model is genuinely improving. We are looking for a practicing specialist rather than a generalist.
This role is fully remote.
2. Key Responsibilities
- Expert review: Assess physics tasks and model outputs, catching flawed derivations, unjustified approximations, dimensional and limit errors, and answers that read well but would not survive peer review.
- Problem specs and reference solutions: Write precise problem statements and rigorous reference solutions that reflect how research physics is actually done.
- Benchmarks: Design challenging, research-level problems and evaluation sets in your area of specialization.
- Calibration: Work with other researchers and experts in adjacent fields to turn tacit expert judgment into explicit, teachable criteria.
3. Core Qualifications
- Education: PhD in physics, astrophysics, applied physics, or a closely related field.
- Seniority: A faculty appointment, principal investigator, staff or senior scientist, or an equivalent senior research role at a university, national laboratory, or research organization.
- Domain depth: Genuine specialization in at least one area, for example condensed matter, high-energy or particle physics, astrophysics and cosmology, atomic, molecular, optical and quantum physics, or statistical and computational physics.
- Research record: A strong peer-reviewed publication record. Recognition such as competitive fellowships or awards is a plus.
- AI fluency: Hands-on use of large language models in your work, and the judgment to tell a sound argument from a plausible-sounding wrong one.
- Communication: Excellent written communication and the ability to give precise, well-structured feedback.
- Location: Based in the United States.
Description from Mercor. Full details and the application are on Mercor's site.
About Mercor
Mercor matches professionals with AI labs that need expert judgment: evaluating, writing and correcting model output in fields from law and medicine to software. You apply with a résumé and a short interview led by an AI, taken whenever suits you. Work is paid by the hour, every week, into your bank account.
All Mercor roles →