Math Olympiad Pro | AI Model Reasoning Evaluator

Braintrust is looking for a candidate to work on pioneering AI projects by crafting challenging mathematics problems and rigorously evaluating the performance of large language models. This role entails original problem authorship, evaluation of model responses, and diagnosis of reasoning errors.

Required qualifications include expertise in competitive mathematics and structured written communication. You will work remotely, needing a desktop setup and good internet connection. The position is a contractor assignment for 3 months, requiring a commitment of 40 hours a week.