Math Experts for AI Training

About the role

Gramian Consultancy is seeking highly analytical individuals with a strong background in computational mathematics to support advanced AI evaluation projects. The role involves designing mathematical problems that test the limits of large language models and producing clear, step‑by‑step solutions.

Key responsibilities

• Design and solve challenging mathematics problems to probe LLM capabilities.
• Produce high‑quality, detailed solutions with explicit reasoning.
• Collaborate with LLM researchers to align problems with evaluation goals, focusing on abstraction, multi‑step reasoning, and symbolic manipulation.
• Help define new benchmark suites covering topics from early undergraduate to PhD‑level curricula.

Required profile

• Master’s, Ph.D., or current Ph.D. candidate in Mathematics, Applied Mathematics, or Statistics.
• Strong research and analytical skills with the ability to break down complex problems.
• Availability for 8 hours per day with a 4‑hour overlap with Pacific Standard Time.
• Contract duration of at least 10 weeks, remote work from listed eligible countries.

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

• Contract‑based assignment with flexible remote work.
• Opportunity to influence AI evaluation methodologies.