Mathematics Expert (Master's/Ph.D.)

What you'll do

You push language models on mathematics and mark where they fail. The ad lists:

• Designing original, hard problems, especially multi-step, abstract and proof-based
• Solving problems yourself and writing structured solutions with justification
• Reviewing model solutions, finding errors or missing arguments, and annotating corrections
• Helping define evaluation benchmarks across curricula from early undergraduate to PhD
• Writing and validating Python solutions with approved scientific libraries
• Theorem-prover tasks in Lean: translating problems and proofs into formal language and checking that they compile

Who fits

• Solid maths foundations, at the level of engineering entrance exams and graduate or PhD programmes
• Ability to explain concepts simply
• Research and analytical skills, creative thinking, independence and clear written communication
• Preferred: people pursuing or holding a master's, Ph.D. or postdoc in mathematics, applied mathematics, statistics or a related field

What it pays

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

Worth knowing

Good:

• Unusually broad: proof writing, Python and Lean in one role
• Students are eligible
• Possible extension based on performance and project needs

Less good:

• At least 4 hours a day and 20 hours a week, with 4 hours of overlap with PST (options of 20, 30 or 40 hours)
• Contractor assignment, no medical or paid leave
• No length, countries or assessment details in the ad
• Lean experience is not listed as a requirement but is part of the work

About this listing

Turing first posted this role on 20 May 2025 and the ad was read from its job board on 18 October 2026. See Turing.