Remote AI Coding QA Analyst & Red-Teamer

Data Annotation is seeking a contributor to run agentic coding sessions on real engineering tasks, analyze what the models produce, and red-team them until they fail in interesting ways. You’ll vibe-code with frontier models to fix bugs, extend APIs, ship features, and see how far the model gets on its own, then assess the AI's reasoning against production standards. This is a remote, contract-style role with flexible hours.