Computational Mathematician: AI Benchmark Problem Designer

Mercor; Greater London; Remote; GBP 109,000 - 218,000; Part time

Job summary

Mercor is seeking PhD and Master's scientists to author AI evaluation tasks for Sci Code. You will create original, executable research problems that frontier models cannot solve, contributing to a new benchmark in scientific computing.

Responsibilities include sourcing material, writing prompts, and building grading criteria, with calibration against frontier models to ensure challenge and rigor.

Qualifications

• PhD in mathematics, applied mathematics, computational mathematics, or closely related field.
• Depth in at least two of: numerical linear algebra, computational mechanics, computational finance.
• Working proficiency in Python or R for scientific computing.
• Familiar with Git/GitHub and running code in Docker with PR workflow.

Responsibilities

• Source your own material: a published paper, a Kaggle dataset, an open-source repository, or a designed scenario.

Skills

Python

R

Git/GitHub

Docker

Education

PhD in Mathematics

Master's in a related field

Tools

Docker

GitHub Actions

Job description

Mercor is seeking PhD and Master's scientists to author AI evaluation tasks for Sci Code. You will create original, executable research problems that frontier models cannot solve, contributing to a new benchmark in scientific computing.

Responsibilities include sourcing material, writing prompts, and building grading criteria, with calibration against frontier models to ensure challenge and rigor.