Co-op, LLMs for Decision Making

Co-op focused on integrating large language models with Bayesian optimization to prototype ML methods for experimental campaigns. You’ll prototype approaches that combine LLM reasoning with Bayesian optimization, develop evaluation frameworks to benchmark LLM-augmented strategies against Bayesian baselines, help integrate promising methods into the decision making stack used across physical science campaigns, and document findings through write-ups, presentations, or contributions to internal libraries. Strong Python skills, familiarity with ML frameworks (PyTorch, JAX), foundation in Bayesian methods, and experience with LLMs (fine-tuning, benchmarking) are expected; the role emphasizes turning open-ended scientific decision-making questions into concrete ML tasks and collaborating across ML and physical science teams. Bonus points for experience with active learning, design of experiments, multi-objective optimization, or agentic frameworks in scientific settings.