AI Coding Agent Evaluator - Design & QA Real-World Tasks

Mindrift is seeking specialists for project-based AI opportunities focused on evaluating AI coding agents. You will build realistic developer environments, design challenging tasks, and write tests to evaluate solutions.

The role requires over 5 years of software development experience and proficiency in Python (FastAPI) and JavaScript (React). This position offers flexibility in hours, with compensation of up to $40/hr based on performance.

Build realistic developer environments with codebase and infrastructure. Design tasks that challenge AI coding models. Write tests to verify agent solutions. 5+ years in software development. Experience writing functional and integration tests. Deep understanding of AI coding tasks.