Skip to content
OpenTrain AIFor AI Companies

Physics Expert for LLM Evaluation

Design and solve difficult physics problems that test large language models, then write clear solutions and feedback. This remote contractor role needs strong physics knowledge, excellent English, and at least 20 hours each week.

Apply now
OpenTrain AI

Generative AI & RLHF

100% Remote

Contract, part-time

Engagement

Remote

Location

Jul 17, 2026

Posted

Open worldwide

The work

You will create and solve challenging physics problems that show where large language models struggle. Your work will support model evaluation and fine-tuning by testing abstraction, multi-step reasoning, and symbolic problem-solving.

You will work with LLM researchers to shape evaluation materials and help build physics benchmarks ranging from early undergraduate topics through PhD-level material.

  • Design complex physics problems for language-model evaluation.
  • Solve problems in classical mechanics, electromagnetism and optics, and thermodynamics and statistical physics.
  • Write accurate, step-by-step solutions with clear reasoning.
  • Give detailed annotations and constructive feedback.
  • Help define physics evaluation benchmarks across undergraduate through PhD-level curricula.
  • Explain advanced physics ideas in simple language, including through visuals and reasoning.
  • Work independently and collaborate remotely with LLM researchers.

What it pays and takes

This is a part-time freelance contractor assignment. The listing does not specify a pay rate. The work may be extended based on performance and project needs.

  • Hours: 20 or more hours per week.
  • Location: Remote and open worldwide.
  • Language: Excellent English comprehension and structured communication skills.
  • Level: Listed as entry level, with a strong foundation in physics, applied physics, or a related field required.
  • Relevant study: Master's, PhD, or postdoctoral study in physics, applied physics, or a related field is encouraged.
  • Skills: Complex problem solving, logical analysis, clear explanation, research, creativity, and lateral thinking.
  • Equipment: A reliable desktop or laptop and a good internet connection.
  • Work arrangement: Individual freelance contractor and part-time assignment.

How it works

Apply on OpenTrain with your resume, then complete the application on the hiring site.

About AI training work

AI training is the human work behind systems that learn from examples, including writing and rating model responses and evaluating their reasoning. Physics experts are needed to create accurate problems and judge solutions that require real subject knowledge.

Requirements

  • Experience: Entry level
  • Languages: English

How to apply

  1. Apply here on OpenTrain. You create a free account, and we send you to the hiring platform.
  2. Complete your application on the hiring platform.

Ready to apply?

Create a free OpenTrain account and apply for this role in minutes.

Keep exploring

Similar open roles

View all AI training jobs

National Park Ranger AI Response Evaluator

Use National Park Service experience to evaluate AI answers about passes, permits, safety, regulations, and trip planning. This US-based contract pays $50 to $150 per hour for 15 to 25 hours per week.

Generative AI & RLHF
Text
Remote · United States
English
Part-time · Flexible
Entry level
Hourly · $50–$150/hr

Posted Oct 13, 2026

Plain-Language Government Services Usability Tester

Review AI-generated answers about public services, identify confusing wording, and suggest clearer alternatives. This flexible, entry-level contract pays $50 to $150 per hour and is open to candidates in the United States.

Generative AI & RLHF
Text
Remote · United States
English
Part-time · Flexible
Entry level
Hourly · $50–$150/hr

Posted Oct 12, 2026

Government Services AI Consumer Reviewer

Review questions and AI-generated answers about services such as Medicare, then give clear feedback that makes public-service information easier to understand. This remote project pays $50 to $150 per hour for about 5 to 10 hours per week.

Generative AI & RLHF
Text
Remote · United States
English
Part-time · Flexible
Entry level
Hourly · $50–$150/hr

Posted Oct 12, 2026

Veterans Benefits AI Evaluation Specialist

Review AI-generated veterans benefits answers for accuracy, completeness, and current guidance. This remote project pays $50 to $150 per hour and requires VA claims experience.

Generative AI & RLHF
Text
Remote · United States
English
Part-time · Flexible
Entry level
Hourly · $50–$150/hr

Posted Oct 12, 2026

Medicare Enrollment AI Evaluation Specialist

Review AI-generated Medicare answers for accuracy, completeness, and realistic enrollment guidance. This remote U.S. contract role pays $50 to $150 per hour and offers 20+ hours per week with asynchronous work.

Generative AI & RLHF
Text
Remote · United States
English
Part-time · Flexible
Entry level
Hourly · $50–$150/hr

Posted Oct 12, 2026