TypeScript Engineer, AI Coding Agent Evaluator
Anywhere
Workplace: RemoteContractUSD 100 - 200 hourlyFunction: Data Science & Machine LearningSkills: ["Engineering judgment","Subjective but rigorous evaluation","Direct feedback","Communication","Attention to explanation quality"]Evaluate the quality of AI coding agent interactions in real-world scenarios. You’ll review end-to-end outputs from tools like OpenAI Codex and Claude Code, focusing on whether responses make sense, reasoning and explanations are useful, and the engineering judgment feels like what a strong engineer would actually do. Provide clear, opinionated, subjective-but-rigorous feedback and help define what “great” looks like when using Cursor and similar AI-first developer workflows.
Loading
Loading job details...
Preparing the role view and application actions.

