Computational Particle & Nuclear Physicist for AI Benchmark Design

Design graduate-level computational physics challenges that evaluate whether advanced AI systems can perform research-grade work with real scientific software. This role combines hands-on particle and nuclear physics expertise with rigorous problem design, model testing, and iterative refinement. Role Overview

You will create original problems based on authentic scientific workflows, including simulations, result interpretation, experiment design, and extracting hidden information from data. Problems may require exact calculations from fully specified setups or strategic planning of queries and experiments to infer information from partial results.

• Develop challenging computational problems requiring skilled use of specialized scientific software.
• Build problems involving multi-step workflows, strategic measurement choices, interpretation of partial results, and efficient narrowing of possible answers.
• Test each problem against advanced AI models and refine it to achieve the intended difficulty.
• Create Python-based problem setups, oracle functions, and solution validators.
• Design challenges where careful reasoning, rather than surface-level pattern matching or raw computation alone, is necessary to reach the correct result.

• Graduate-level training in a relevant STEM field, including an MS, PhD, or equivalent research experience.
• Deep hands-on experience with particle and nuclear physics software, especially scikit-hep and related high-energy physics Python tools.
• Experience with particle physics data analysis, cross-section calculations, renormalization group calculations, and perturbative QCD.
• Proven proficiency with at least one relevant scientific software library through research publications, open-source contributions, or professional work.
• Strong Python skills and practical experience applying these tools to real research problems, including understanding their limitations and edge cases.
• Ability to work independently, incorporate feedback into problem designs, and work comfortably in Linux terminal environments and remote compute sandboxes.

• Experience with Monte Carlo event generation or collider phenomenology.
• Experience with other specialized software used in particle and nuclear physics.
• Experience across multiple relevant domains or tools.
• Familiarity with benchmark or evaluation design, scientific teaching, exam or problem-set design, computational reproducibility, or containerized environments.

• Remote, hourly engagement.
• Availability of at least 15 to 20 hours per week.

$70 to $100 per hour.