himalayas.app · posted 2026-08-12
Freelance Agent Evaluation Engineer
Unknown company · Backend Engineer · L3 · remote
Summary
Mindrift seeks a freelance AI evaluation engineer with 5+ years of SWE experience and Python/JS skills to test AI coding agents on a project basis.
Responsibilities
- Build realistic developer environments
- Design AI coding tasks
- Write tests for agent solutions
- Iterate on tasks based on feedback
- Evaluate and improve AI systems
Tools
git
Details
- Industry
- ai
- Stage
- unknown
- Arrangement
- remote
- Languages
- english