Senior Physicist for AI Benchmarking & Evaluation - Remote

Weekday; United States; Remote; USD 124,000 - 193,000; Full time

Job summary

Weekday in the United States is seeking highly experienced PhD Physicists and senior researchers to contribute to the development and evaluation of AI models in physics. You will assess AI model reasoning on physics concepts, design rigorous benchmarks, and craft reference solutions, drawing on your deep domain expertise and hands-on experience with LLMs.

This is a fully remote contractor role with flexible scheduling.

Qualifications

• PhD in Physics or related field.
• Senior academic or research track record at a university, national lab, or equivalent.
• Deep specialization in at least one physics domain and peer-reviewed publications.

Responsibilities

• Expert Evaluation of physics problems and AI-generated outputs for accuracy and rigor.
• Develop precise physics problem statements and detailed specifications.
• Create rigorous reference solutions with mathematical derivations.
• Design complex physics benchmarks to evaluate AI models.

Skills

LLMs experience

Written communication

Education

PhD in Physics

Senior-level research experience

University faculty or PI

Tools

AI tools in research

Job description

Weekday in the United States is seeking highly experienced PhD Physicists and senior researchers to contribute to the development and evaluation of AI models in physics. You will assess AI model reasoning on physics concepts, design rigorous benchmarks, and craft reference solutions, drawing on your deep domain expertise and hands-on experience with LLMs.

This is a fully remote contractor role with flexible scheduling.