Description
Mindrift is recruiting experienced software developers for a project-based opportunity to build and evaluate benchmark tasks for AI coding agents. The work involves creating realistic simulated developer environments, designing solvable coding tasks and evaluation criteria, writing functional and integration tests, and refining tasks based on QA feedback. This is not permanent employment, data labeling, prompt engineering, or primarily writing code from scratch. Applicants need at least five years of software development experience, proficiency with Python/FastAPI, JavaScript/TypeScript/React, Docker, Postgres, Kafka, Redis, testing, and English at B2 or higher. The work is project-based with self-scheduled tasks estimated at about 20 hours each and compensation up to $40 per hour equivalent.
