Pod Lead - Math (Terminal Bench Science) at Turing

Mathematics Pod Lead - Terminal Bench Science | Pay varies | Remote

About the role

Turing, an AI company, is hiring an experienced mathematics expert to lead a pod of 5-10 trainers developing realistic, terminal-based scientific and technical tasks for Terminal Bench Science. You will review tasks for mathematical correctness, reproducibility, challenge, and grader reliability; mentor trainers; and manage quality and throughput so tasks reflect authentic mathematical research and computational workflows. Topics include numerical and applied mathematics, scientific computing, optimization, statistics, mathematical modeling, computational algebra, and formal verification.

What you'll do

• Review tasks end to end: problem statements, datasets, environments, reference solutions, and automated tests.
• Verify mathematical correctness, well-posedness, convergence, stability, conditioning, discretization error, and edge-case handling.
• Ensure tasks require genuine multi-step reasoning rather than lookup or a single library call.
• Confirm appropriate use of exact, symbolic, arbitrary-precision, or floating-point computation, with tolerances suited to each problem's numerical conditioning.
• Design and review graders based on residuals, feasibility, optimality certificates, invariants, error bounds, or proof checking.
• Ensure reproducibility through pinned tools, libraries, solver versions, and dependencies.
• Identify and prevent hard-coded solutions, test-file leakage, and other ways of bypassing the intended computation.
• Mentor and onboard trainers, give precise and actionable feedback, allocate work, monitor quality and throughput, and escalate blockers.
• Maintain pod documentation and collaborate with the Mathematics Team Lead and other stakeholders on benchmark quality.

Requirements

• Ph.D., postdoctoral experience, or equivalent advanced experience in mathematics, applied mathematics, statistics, or a related field.
• Strong programming skills in Python, Julia, C/C++, MATLAB/Octave, or a computer algebra system.
• Strong Linux and terminal proficiency.
• Hands-on experience with numerical methods, scientific computing, symbolic computation, optimization, computational statistics, or mathematical modeling.
• Ability to rigorously evaluate mathematical derivations, algorithms, proofs, and computational results.
• Experience reviewing research outputs, code, mathematical work, or scientific workflows.
• Experience mentoring or leading small technical or research teams.
• Strong written communication and precise, constructive feedback.
• Ability to assess reproducibility, test reliability, and the scientific validity of computational tasks.

Nice to have

• Experience with NumPy, SciPy, SymPy, mpmath, SageMath, PARI/GP, GAP, Macaulay2, or similar workflows.
• Experience with ODE/PDE tools such as FEniCS, Firedrake, DifferentialEquations.jl, or PETSc, and optimization frameworks such as CVXPY, JuMP, Pyomo, or HiGHS.
• Familiarity with proof assistants such as Lean/mathlib, Coq/Rocq, or Isabelle.
• Experience with Docker, Git, CI systems, and automated testing.
• Experience designing benchmarks, competition problems, or computational evaluations, including setting or judging mathematics olympiad problems.
• Experience evaluating AI coding, reasoning, or terminal agents, or prior AI training, data generation, or model evaluation work.
• Publications or open-source contributions in computational mathematics, numerical software, or formalized mathematics.

Pay and schedule

• Contractor assignment; no medical or paid leave.
• At least 4 hours per day and a minimum of 40 hours per week, with 4 hours of overlap with Pacific Time (PST).
• 4-week contract; the expected start date is next week.