Remote ML Engineer: Frontier Code Agent Evaluator

Mercor is collaborating with a leading AI research lab on a project focused on evaluating frontier AI coding models. In this role, you'll use advanced AI coding agents to carry out machine learning engineering tasks, review model-generated implementations, and identify various issues including bugs and performance challenges. The position requires at least 2 years of machine learning engineering experience and familiarity with AI coding agents. The project has a sprint-based commitment with compensation of $400 per accepted task, with each task taking around 2-3 hours to complete. #J-18808-Ljbffr