Remote Physics Domain Expert – AI Benchmark Research

Synthires; United States; Remote; USD 124.000 - 193.000; Teilzeit

Zusammenfassung

Synthires is seeking a Physics Domain Expert for a remote, hourly contract role in the United States. You will apply advanced physics expertise to assess AI-generated physics reasoning, develop rigorous reference solutions, and design benchmarks that push frontier AI models.

The position emphasizes strong written communication, deep specialization in physics, and collaboration with researchers to establish evaluation criteria and provide structured feedback on model reasoning.

Qualifikationen

• PhD in Physics, Astrophysics, Applied Physics, or closely related field.
• Senior research experience as faculty, PI, staff or senior scientist.
• Deep specialization in at least one physics domain (condensed matter, particle physics, astrophysics, cosmology, quantum, computational).
• Hands-on experience using large language models and evaluating scientific reasoning.
• Excellent written communication and analytical skills.

Aufgaben

• Review physics tasks and AI-generated outputs for scientific accuracy and flawed derivations.
• Write precise problem specifications and rigorous reference solutions.
• Develop research-level problems and benchmarks in your area of specialization.
• Collaborate with researchers to establish clear evaluation criteria.
• Provide structured feedback on the quality and reliability of physics reasoning.

Kenntnisse

PhD in Physics

Senior research experience

LLM evaluation experience

Strong written communication

Ausbildung

PhD in Physics or related field

Tools

Large language models

Jobbeschreibung

Synthires is seeking a Physics Domain Expert for a remote, hourly contract role in the United States. You will apply advanced physics expertise to assess AI-generated physics reasoning, develop rigorous reference solutions, and design benchmarks that push frontier AI models.

The position emphasizes strong written communication, deep specialization in physics, and collaboration with researchers to establish evaluation criteria and provide structured feedback on model reasoning.