Description
Mindrift is seeking a project-based Software Engineering Evaluation Specialist focused on Terminal Bench. The specialist designs realistic, self-contained coding tasks for AI coding agents in Docker environments, including broken software, pytest-based verification, instructions, and reference solutions. The role requires at least three years of production backend software development in one supported stack, strong Python and pytest fluency, Docker authoring, Linux and Bash skills, experience with AI coding agents, and B2+ English. Contributions are flexible and part-time in practice, with onboarding and per-task compensation up to $35 per hour; this is not permanent employment.
