Remote ML Engineer: Frontier Code Agent Evaluator

Mercor is seeking contributors for a project with a leading AI research lab to evaluate and improve frontier AI coding models. The role involves using AI coding agents to complete machine learning tasks and assess model performance. Candidates should have over 2 years of professional machine learning engineering experience and familiarity with AI coding tools. Compensation is $400 per accepted task, typically taking 2–3 hours to complete. Candidates will work in sprint-based projects. #J-18808-Ljbffr