Ph.D. / Postdoctoral / Master's Expert

What you'll do

You write problems that language models get wrong, then solve them properly. The ad names areas where models typically struggle (abstraction, multi-step reasoning, symbolic manipulation) and asks you to produce clear, step-by-step solutions with well-articulated reasoning. You work with LLM researchers so each problem lines up with an evaluation goal, and you help define new benchmarks across STEM curricula from early undergraduate to PhD level.

The wording of the ad leans on Physics for the benchmark work, while the skill tags span physics, mathematics, chemistry and biology, so expect the exact subject to depend on the project. The ad does not say how subjects are assigned.

Who fits

• A solid STEM foundation, at the level of engineering entrance exams and graduate or PhD programs
• Candidates currently pursuing a Master's, PhD or postdoc in STEM or applied physics are eligible and encouraged to apply (listed as a preferred qualification)
• Good research, analytical and feedback skills, and creative, lateral thinking
• Ability to explain concepts simply, with visuals where helpful
• A desktop or laptop with a good internet connection, and self-motivation in a remote setting

What it pays

The ad does not publish a rate or hours. Turing sets rates per project; see Turing.

Worth knowing

Good:

• Current students and researchers can apply, not only people with finished degrees
• Fully remote, with possible contract extension based on performance and project needs
• You get hands-on experience seeing where frontier models fail

Less good:

• No pay figure, hours or contract length are stated
• The subject area is not pinned down by the ad
• Contractor assignment with no medical or paid leave
• Posted since July 2025, so check availability

About this listing

Posted on Turing's job board on 24 July 2025 and read on 18 October 2026. Requirements and perks are Turing's own text; the note on the unclear subject scope is ours. See Turing.