AI Evaluation Engineer - Flexible, Project-Based

Mindrift is building a dataset to evaluate AI coding agents by creating realistic developer environments and tasks. You will design evaluation tasks, craft tests, and iterate based on QA feedback, ensuring fair assessment of model capabilities.

This role focuses on constructing challenging, trainable tasks rather than traditional coding from scratch. Applicants should have 5+ years in software development, strong Python (FastAPI) and JavaScript/TypeScript (React) skills, experience with Docker,