Shan Chen is a Research Scientist at R37, R1's AI innovation lab, where he specializes in evaluating and improving large language models and developing agentic AI systems for healthcare. His work focuses on advancing AI reliability, clinical safety and accuracy to support complex healthcare workflows.
At R37, Shan applies his expertise in natural language processing, AI evaluation and model post-training to develop intelligent systems for medical coding and denial appeals. His research emphasizes evidence-grounded reasoning across complex clinical records, helping AI systems interpret medical information, reduce hallucinations, and adapt to the requirements of different healthcare providers and payers.
Before joining R1, Shan earned his Ph.D. cum laude from Maastricht University through a joint research program with Harvard–Mass General Brigham Artificial Intelligence in Medicine (AIM). His research explored the reliability, safety and performance of language models in clinical settings, with particular emphasis on improving how AI systems interpret and reason over medical information.
Shan received the prestigious 2024 Google PhD Fellowship in Natural Language Processing. His research has appeared at leading AI conferences and in medical journals. His expertise in clinical AI and language model evaluation brings a valuable perspective to R1's efforts to develop reliable, intelligent technology that improves healthcare operations.