Sepal AIDomain experts
Physics PhD Reasoning Benchmark
up to $100/hr
About this role, in Sepal AI's words
We're developing novel methods to evaluate how well AI systems can reason through advanced physics workflows. This project sits at the cutting edge of AI evaluation—where physics domain knowledge meets frontier model assessment. We're seeking Physics PhD holders (or ABDs) with strong conceptual depth and computational modeling experience to help us design and review high-quality physics problem sets that test AI’s capabilities in solving real-world physics challenges.
What you'll do
- Design rigorous, graduate-level physics tasks and rubrics to assess AI reasoning across topics like classical mechanics, quantum systems, thermodynamics, and electrodynamics.
- Contribute example solutions and grading rubrics that assess reasoning steps, not just final answers.
- Collaborate with our internal team and other domain experts to probe the strengths and failure modes of advanced AI models.
- Provide expert feedback on task quality, correctness, ambiguity, and conceptual coverage.
Candidate background
What We're Looking For
- PhD or ABD in Physics, Applied Physics, or a closely related discipline.
- Strong ability to distill complex physics problems and guide others through the reasoning.
- Demonstrated experience in computational modeling or numerical analysis (e.g., simulations, data pipelines, Monte Carlo methods, FEA).
- Familiarity with at least one of: Python, MATLAB, Mathematica, Julia, C++, COMSOL, ROOT, Geant4, or equivalent scientific tooling.
- Experience with publishing, teaching, or curriculum design is a plus.
- Ideal candidates will be comfortable with both problem design and conceptual review, especially for graduate-level tasks.
Quoted from selected sections of Sepal AI's posting. The full posting may state other conditions. Read the full posting
A closer look
More context, when you need it.
Full job descriptionThe original posting, in Sepal AI's words
Posted by Sepal AI, reproduced here so you can judge the role before clicking. Original posting ↗
We're developing novel methods to evaluate how well AI systems can reason through advanced physics workflows. This project sits at the cutting edge of AI evaluation—where physics domain knowledge meets frontier model assessment. We're seeking Physics PhD holders (or ABDs) with strong conceptual depth and computational modeling experience to help us design and review high-quality physics problem sets that test AI’s capabilities in solving real-world physics challenges.
What You'll Do - Design rigorous, graduate-level physics tasks and rubrics to assess AI reasoning across topics like classical mechanics, quantum systems, thermodynamics, and electrodynamics. - Contribute example solutions and grading rubrics that assess reasoning steps, not just final answers. - Collaborate with our internal team and other domain experts to probe the strengths and failure modes of advanced AI models. - Provide expert feedback on task quality, correctness, ambiguity, and conceptual coverage.
What We're Looking For - PhD or ABD in Physics, Applied Physics, or a closely related discipline. - Strong ability to distill complex physics problems and guide others through the reasoning. - Demonstrated experience in computational modeling or numerical analysis (e.g., simulations, data pipelines, Monte Carlo methods, FEA). - Familiarity with at least one of: Python, MATLAB, Mathematica, Julia, C++, COMSOL, ROOT, Geant4, or equivalent scientific tooling. - Experience with publishing, teaching, or curriculum design is a plus.
Ideal candidates will be comfortable with both problem design and conceptual review, especially for graduate-level tasks.
Compensation & Logistics - Hourly Rate: $65–$100/hour depending on experience and task complexity. - Type: Contract, flexible hours (part-time and full-time options). - Location: Remote (US preferred); Bay Area availability is a bonus
How does the pay compare?Across Domain experts roles, not this role alone
From our own daily reads of every open listing on the platforms we follow, not from Sepal AI's posting. How we count.
Pay across the field: Domain experts
Across 1481 roles in this field with a stated hourly rate in US dollars, on 25 platforms, the middle half pays $65 to $125 an hour at the top of the range, and the median is $90. This role's top rate, $100, is in the middle half. Of the 435 distinct rates we count, 232 are lower and 170 are higher.
| Platform | Roles | Top of range, per hour |
|---|---|---|
| micro1 | 255 | $14 to $400 · median $105 |
| Handshake AI | 190 | $30 to $300 · median $85 |
| Mercor | 167 | $35 to $350 · median $120 |
| Alignerr | 162 | $20 to $200 · median $80 |
| AfterQuery | 131 | $45 to $200 · median $100 |
Sources and listing historyWhere this information comes from
This listing's history
- First seen here on 15 Nov 2026, and still on Sepal AI's list when we last read it on 21 Nov 2026.
- The listed pay has not changed since then.
- Posted by Sepal AI
- Not stated
- First seen by AIPayList
- Last seen live
- Listing ID
- 59dfc5b8-1e4a-4d2b-bdff-f8470cae7841
Pay as the source states it: “Rate: $65-$100/hour”.
Platforms sometimes change a rate after posting. Every listing here is re-read at least once a day and corrected when its source moves, so a difference you see on the platform is usually a change made since the last read. How freshness works.
Keep exploring
More like this
Related field, different requirements. Check each role's own page before you apply.