AI Model QA & Red-Team Engineer (Remote)

DataAnnotation is seeking a coder who can run agentic coding sessions on real engineering tasks, analyze model outputs, and red-team them until they fail in interesting ways. Every failure you document teaches the next generation of coding agents. You’ll vibe-code with frontier models on real tasks: fix a bug, extend an API, ship a feature, and assess how far the model can go on its own. Clear written English is essential.