As a Research Scientist Intern at Mercor, you will contribute to cutting-edge research in areas such as post-training, reinforcement learning with verifiable rewards (RLVR), data generation, and model evaluation. You will investigate the impact of datasets, rewards, and training methods on large language models' capabilities and behavior. This role involves designing experiments, developing new evaluation methodologies, conducting failure analysis, and testing approaches to enhance tool use, agentic behavior, and real-world reasoning. You will collaborate closely with research scientists, engineers, and domain experts to transform open-ended questions into rigorous experiments, contributing to Mercor's research agenda and potentially supporting external publications and the development of advanced AI systems.
San Francisco onsite Intern PythonFine-TuningReinforcement Learning +8 more