Summer 2027 PhD Gen AI and Reinforcement Learning Research Intern

Conduct research and prototype methods for post-training large generative models, including policy optimization, preference learning, reward modeling, and credit assignment. Develop approaches to improve reasoning, code generation, tool use, and agentic behavior, then design controlled, verifiable experiments to study failure modes like reward hacking and training instability. Create evaluations for quality, robustness, safety, and real-world task performance, and collaborate on training, logging, rollout generation, and reproducibility while documenting results for technical reports.