Mathematics Model Evaluators (AI Data Trainers)
Core
Design and solve challenging Mathematics problems to probe the limitations of large language models and create clear, step-by-step solutions with well-articulated reasoning.
Role type
Senior IC mathematics model evaluator (AI data trainer)
Builds
Evaluation benchmarks and datasets for fine-tuning large language models
Domain
Artificial Intelligence / Mathematics
Deliverable
production ML models
Required skills
Advanced Mathematics (PhD-level), Analytical reasoning, Problem decomposition, Clear technical communication, LLM evaluation methodology, Research skills
Preferred skills
Experience with symbolic manipulation, Multi-step reasoning, Abstraction, Creative lateral thinking
Technologies
Magma, Macaulay2, Singular, GAP, SageMath, Polymake, 4ti2, LattE, DIPHA, PHAT, AUTO-07P, XPPAUT, Perseus, Stan, PyMC, OR-Tools, Z3, PARI/GP, fpLLL
Responsibilities
Design and solve challenging Maths problems to probe LLM limitations, Create clear, high-quality, step-by-step solutions with well-articulated reasoning, Collaborate with LLM researchers to align problems with evaluation goals, Help define new evaluation benchmarks based on Mathematics curricula
Seniority
Senior, hands-on IC