What the work actually involves

Each task you produce is a small, self-contained scientific problem set: one main problem plus at least three sub-problems that build logically toward it. For every part you write a golden solution in Python, cover it with unit tests, and design those tests so they actually separate a correct implementation from a plausible-looking wrong one. A test that passes whenever the output is the right shape is worthless here — discriminativeness is scored explicitly.

Tasks then go through QC on Turing's Central Task Platform: Tier 1 structure checks, Tier 2 quality rubrics, and Pass@K evaluation against multiple LLM judges (GPT, Gemini, Nemotron). Problems that every model solves on the first attempt, or that no model can solve because the specification is ambiguous, both get sent back. You will spend real time iterating on feedback, and your rework rate is tracked — the stated target is consistent L1 approval on first submission.

What the screen looks for

  • A Master's or PhD in a STEM field, and the ability to talk about a specific subfield in enough detail to generate non-trivial problems in it
  • Working Python for scientific computing: NumPy, SciPy, SymPy or domain-specific stacks, plus comfort writing tests
  • Judgment about well-posedness and determinism — fixed seeds, stated tolerances, no floating-point ambiguity, no reliance on external data or network calls
  • Prior exposure to AI data annotation, LLM evaluation, or coding benchmarks is treated as a real advantage rather than a formality

Logistics

Remote, contractor engagement with no paid or medical leave, 8-week contract duration. Commitment is 40 hours per week with at least four hours overlapping PST, and you are expected on sync calls for reviews, feedback sessions, and standups. Eligibility is restricted to residents of Bangladesh, Brazil, Colombia, Egypt, Ghana, India, Pakistan, Indonesia, Kenya, Nigeria, Turkey, and Vietnam. Pay is not disclosed in the listing; ask for the rate and the per-task versus hourly structure before you commit to a full-time schedule.