Senior Software Engineer for AI Task Evaluation (Remote)

Braintrust is seeking a skilled developer with strong Python experience to help evaluate AI coding agents. You will create realistic developer environments, design developer tasks, and write verifying tests. This project-based role requires 30+ hours per week availability and effective communication in a remote context.

The ideal candidate will be proficient in FastAPI, pytest, and asynchronous programming, and have hands-on experience with Docker and PostgreSQL. Join us in this challenging yet rewarding opportunity!