Part-Time Agent Evaluation Specialist at Mindrift

Elevate AI capabilities as a Part-Time Agent Evaluation Specialist with Mindrift, working on innovative tasks to evaluate AI coding agents. Bring your software and testing expertise to a dynamic project-based environment.

In this role, you will develop complex tasks to assess how well AI coding models can perform real developer duties. We seek candidates with 5+ years in software development, adept in Python and familiar with full-stack technologies. Your focus will involve creating criteria, testing solutions, and providing valuable feedback regarding AI performance.

Key Responsibilities: • Construct virtual environments to evaluate coding tasks • Generate and refine evaluation criteria and tasks • Design developer workstation simulations • Develop tests for accurate evaluation of solutions • Engage interactively with AI agents to validate outcomes

Requirements: • Computer Science degree or related discipline • 5 years experience in software development • Ex...