Mindrift is building a dataset to evaluate AI coding agents by creating realistic developer scenarios, environments, and evaluation criteria. You’ll craft tasks from simulated states, write tests, and iteratively refine the tasks based on QA feedback.
This project-based role focuses on guiding and evaluating agent solutions rather than writing code from scratch. Compensation scales with the level and pace, up to $40/hr equivalent.
#J-18808-Ljbffr