Mindrift is building a dataset to evaluate AI coding agents by creating tasks, tests, and realistic environments for AI agents to solve. You’ll design tasks, write tests, and iterate based on QA feedback, ensuring a range of valid solutions are accepted.
This is a project-based, non-permanent role focused on evaluating and refining model performance. We look for developers with 5+ years of software experience and a strong stack (Python/FastAPI, React, Docker, Postgres, Kafka, Redis) and solid
#J-18808-Ljbffr