Loading...
Mercor is seeking experienced researchers and technical experts to contribute to a project supporting a frontier-model evaluation effort focused on agentic workflows. You’ll design and validate challenging benchmark tasks in data science, machine learning, finance, and coding to help surface and diagnose reasoning and problem-solving gaps in a target STEM model. The work centers on building robust, real-world tasks with executable tests and then analyzing model/agent behavior.
Apply directly on Mercor to get started.