Frontier High-Energy Physics Researcher: Golden References

Obsidian; New York (NY); On-site; USD 110,000 - 186,000; Part time

Job summary

Obsidian seeks expert physics researchers to author and verify golden reference solutions for the CritPt benchmark (arXiv:2509.26574v3). You will solve research-level problems end-to-end, audit peers, and adjudicate between attempts to produce 100%-human-verified data for evaluating frontier physics reasoning.

Applicants should have PhD-level credentials, familiarity with LaTeX, Python, Jupyter, and SymPy, plus strong English skills.

Qualifications

• PhD or postdoc in the relevant physics subfield (senior PhD student minimum).
• Postdoc or junior professor in the relevant subfield (PhD minimum).
• Full professor or industry PI in the relevant subfield (senior postdoc or junior professor minimum).
• Hands-on familiarity with at least two canonical methods of the target subfield (publications preferred).
• 3–5 representative publications (arXiv ID or DOI) in the last ~5 years.

Responsibilities

• Solve research-level physics challenges end-to-end with verifiable derivations, code, and references.
• Decompose challenges into checkpoint sub-problems requiring genuine physical reasoning.
• Author Python answer templates with auto-grading functions for symbolic or numerical answers.
• Audit submitted solutions for correctness, scope, and method soundness; provide iterative feedback.
• Adjudicate between parallel solver attempts and decide which becomes the golden reference.
• Document chain-of-thought reasoning, error tolerances, and verification tests.

Skills

Research leadership

Publications awareness

English proficiency

Problem decomposition

Adjudication expertise

Education

PhD or postdoc in subfield

Tools

LaTeX

Python

Jupyter

SymPy

Job description

Obsidian seeks expert physics researchers to author and verify golden reference solutions for the CritPt benchmark (arXiv:2509.26574v3). You will solve research-level problems end-to-end, audit peers, and adjudicate between attempts to produce 100%-human-verified data for evaluating frontier physics reasoning.

Applicants should have PhD-level credentials, familiarity with LaTeX, Python, Jupyter, and SymPy, plus strong English skills.