Pod Lead - Physics (Terminal Bench Science) at Turing

Physics Pod Lead | Varies | Remote

Turing is an AI company that works with leading AI labs and builds real-world AI systems. They are hiring an experienced physics expert to lead a pod of trainers building realistic, terminal-based scientific tasks for Terminal Bench Science. You will review every task for physical correctness, reproducibility, and grader reliability, and coach trainers to deliver challenging work.

What you'll do

• Review trainer tasks end to end: task statements, datasets, simulation inputs, environments, reference solutions, and automated tests.
• Verify that tasks reflect authentic physics workflows and require genuine multi-step reasoning.
• Check that tools, libraries, and dependencies are pinned and results are reproducible.
• Validate dimensional consistency, unit systems and conventions, conservation laws, symmetries, integrator energy drift, convergence, and statistical treatment of uncertainties.
• Ensure tolerances allow legitimate stochastic and numerical variation without accepting physically incorrect results.
• Ensure graders test observables, fitted parameters, uncertainties, or physical invariants rather than formatting, and that tasks cannot be gamed with hard-coded outputs or bypassed computation.
• Give clear, actionable written feedback and track revisions through closure.
• Onboard and mentor trainers; allocate work, track quality and throughput, and escalate blockers.
• Maintain pod documentation covering guidelines, recurring issues, and exemplary tasks.

Requirements

• Ph.D., postdoctoral experience, or equivalent advanced experience in physics.
• Strong programming skills in Python, C/C++, Julia, or Fortran, with Linux proficiency.
• Hands-on experience with computational physics, simulation, or physics data analysis.
• Proven experience reviewing code, analyses, or research outputs.
• Experience mentoring or leading small technical or research teams.
• Excellent written communication skills for precise, constructive feedback.

Preferred

• Familiarity with QuTiP, Qiskit, Kwant, ITensor, ROOT, Geant4, Astropy, Dedalus, MEEP, or similar tools.
• Familiarity with Docker, Git, CI systems, and automated testing.
• Experience designing benchmarks or simulation-based evaluations.
• Experience evaluating AI coding or terminal agents, working in large collaborations with formal internal review, or prior work in AI training or evaluation programs.

Pay and schedule

• Contractor assignment; no medical or paid leave.
• 4-week contract; expected start date is next week.
• At least 4 hours per day and a minimum of 40 hours per week, with 4 hours of overlap with PST.
• Pay is not listed and varies by applicant.