Math Experts for AI Training

About the role

We are seeking highly analytical individuals with a strong background in computational mathematics to help design and evaluate advanced AI systems. The role involves creating challenging mathematics problems to test large language models and collaborating with researchers to develop new evaluation benchmarks.

Key responsibilities

• Design and solve complex mathematics problems that probe the limits of large language models.
• Produce clear, step‑by‑step solutions with well‑articulated reasoning.
• Work with LLM researchers to align problems with evaluation goals, focusing on areas such as abstraction, multi‑step reasoning, and symbolic manipulation.
• Help define new benchmark datasets covering topics from early undergraduate to PhD‑level mathematics.

Required profile

• Master’s, Ph.D., or currently pursuing a Ph.D. in Mathematics, Applied Mathematics, or Statistics.
• Strong research and analytical abilities.
• Ability to work 8 hours per day with a 4‑hour overlap with Pacific Standard Time.
• Available for a contract of at least 10 weeks.

Required skills

• Proficiency in at least three of the following tools: Magma, Macaulay2, Singular, GAP, SageMath, Polymake, 4ti2, LattE, DIPHA, PHAT, AUTO‑07P, XPPAUT, Perseus, Stan, PyMC, OR‑Tools, Z3, PARI/GP, fpLLL.

What we offer

• Contractor assignment (no medical or paid leave).
• Remote work with flexible location across multiple countries.
• Opportunity to influence AI evaluation research.