Remote Math & Benchmark Lead for AI Training Pods

Turing; Turkey; On-site; TRY 413,000 - 744,000; Full time

Job summary

Turing seeks an experienced Mathematics expert to lead a pod of 5–10 trainers creating terminal-based scientific tasks for Terminal Bench Science. You will review mathematical correctness, design graders, and mentor trainers to ensure authentic research workflows.

You will oversee numerical methods, optimization, statistics, and formal verification, validating reproducibility and rigor across tasks and datasets.

Qualifications

• 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 the ability to provide precise, constructive feedback.
• Ability to assess reproducibility, test reliability, and the scientific validity of computational tasks.

Responsibilities

• Review tasks end to end, including 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.
• Validate that exact, symbolic, arbitrary‑precision, or floating‑point computation is used appropriately.
• Check that tolerances are suitable for the problem’s numerical conditioning.
• Design and review graders based on mathematical properties such as residuals, feasibility, optimality certificates, invariants, error bounds, or proof checking.
• Ensure tasks are reproducible through pinned tools, libraries, solver versions, and dependencies.
• Identify and prevent hard‑coded solutions, test‑file leakage, and other methods of bypassing the intended computation.
• Provide precise, actionable feedback and track trainer revisions through closure.
• Mentor and onboard trainers on mathematical rigor, task design, coding practices, and evaluation standards.
• Allocate work, monitor quality and throughput, and elevate blockers.
• Maintain pod documentation covering guidelines, recurring issues, and exemplary tasks.
• Collaborate with the Mathematics Team Lead and other technical stakeholders to improve benchmark quality.

Skills

Python

Julia

C/C++

MATLAB/Octave

Linux

Education

Ph.D. or equivalent in mathematics

Tools

Docker

Git

CI systems

Automated testing

Job description

Turing seeks an experienced Mathematics expert to lead a pod of 5–10 trainers creating terminal-based scientific tasks for Terminal Bench Science. You will review mathematical correctness, design graders, and mentor trainers to ensure authentic research workflows.

You will oversee numerical methods, optimization, statistics, and formal verification, validating reproducibility and rigor across tasks and datasets.