Review and validate mathematical tasks for scientific accuracy and rigor. About Turing: Turing is one of the world’s fastest-growing AI companies, accelerating the advancement and deployment of powerful AI systems.
About the role
Review and validate mathematical tasks for scientific accuracy and rigor. About Turing:
Turing is one of the world’s fastest-growing AI companies, accelerating the advancement and deployment of powerful AI systems.
Turing helps customers in two ways: Working with the world’s leading AI labs to advance frontier model capabilities in thinking, reasoning, coding, agentic behavior, multimodality, multilinguality, STEM and frontier knowledge; and leveraging that work to build real-world AI systems that solve mission-critical priorities for companies.
Role Overview
We are seeking 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 trainer-created tasks for mathematical correctness, reproducibility, challenge, and grader reliability. You will also mentor trainers, manage quality and throughput, and ensure that tasks reflect authentic mathematical research and computational workflows.
The role covers numerical and applied mathematics, scientific computing, optimization, statistics, mathematical modeling, computational algebra, and formal verification.
What you’ll do
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. …
Official source: work.turing.com. Details can change; the platform's page is the final word. How we check listings.
