Senior Software Engineer - AI Evaluation & Testing

Braintrust is looking for an experienced software developer to evaluate AI coding agents through realistic task creation. The ideal candidate will have over 5 years of experience in software development, proficient in Python and JavaScript/TypeScript, and capable of writing integration tests.

This role demands a deep understanding of coding models and the ability to design nuanced tasks that push these models to their limits. Flexibility is provided regarding task completion timing.