Description
Mindrift is recruiting experienced software developers for a project-based opportunity to create and evaluate benchmark tasks for AI coding agents. The work involves building realistic simulated developer environments, designing coding tasks and acceptance criteria, writing functional and integration tests, and refining evaluations based on QA feedback. The role is not permanent employment, data labeling, prompt engineering, or primarily writing code from scratch. Tasks are estimated at 30 hours each, work is flexible but deadline-driven, and compensation is paid per accepted task at up to the equivalent of $200 per hour.
