AI Evaluation Scientist - Math PhD (6-Week, Part-Time)

Mercor is hiring PhD and Master's scientists to author AI evaluation tasks (Sci Code) for a new benchmark in scientific computing. You will develop original, executable research problems that frontier models cannot solve. Expect depth in multiple subdomains, such as numerical linear algebra, computational mechanics, or computational finance, with strong Python and Docker/GitHub fluency to ensure high-quality, reproducible runs within a PR workflow. #J-18808-Ljbffr Mercor