YLab at Harvard Medical School and Brigham and Women’s Hospital, jointly with Professor Joshua Lin, is recruiting a postdoctoral fellow in Agentic AI for Healthcare.

The fellow will work with Prof. Jie Yang and Prof. Joshua Lin on building, evaluating, and deploying AI agents for real-world clinical, pharmacoepidemiology, and biomedical settings. The position is ideal for candidates interested in large language models, agentic workflows, clinical natural language processing, electronic health records, multimodal medical data, pharmacoepidemiology, and trustworthy AI systems.

Research Directions

  • Agentic AI systems for clinical reasoning, care delivery, and biomedical discovery
  • Large language model agents that use tools, retrieve evidence, and interact with clinical data
  • Agentic AI and large language models for pharmacoepidemiology and real-world evidence generation
  • Evaluation, safety, and alignment of AI agents in healthcare settings
  • Clinical NLP, EHR phenotyping, patient trajectory modeling, and real-world evidence generation
  • Human-AI collaboration for clinicians, researchers, and patients

Environment and Resources

The fellow will join an interdisciplinary research group with access to substantial clinical data, computing, and collaborators across Harvard Medical School, Brigham and Women’s Hospital, Mass General Brigham, Broad Institute, Harvard Data Science Initiative, and Kempner Institute.

The group has a strong publication record in venues including Nature Biomedical Engineering, New England Journal of Medicine AI, JAMA Network Open, npj Digital Medicine, and leading AI conferences such as NeurIPS, ACL, EMNLP, AAAI, WWW, and IJCAI.

Available research resources include:

  • EHR records for over 8 million patients from Mass General Brigham, the largest health care system in Massachusetts, across 12+ Harvard-affiliated hospitals
  • Hundreds of millions of patient-level insurance claims
  • More than 200 million real-world EHR notes linked with insurance claims data
  • Rich follow-up assessment data for real-world evidence studies
  • 100 open-access clinical text datasets
  • 20 advanced GPUs including H100, H200, and RTX Pro 6000 GPUs
  • Strong collaborations with world-leading pharmacoepidemiology experts, clinicians, biomedical informaticians, machine learning researchers, and public health scientists

Qualifications

Applicants should have, or expect to receive, a PhD in computer science, biomedical informatics, machine learning, computational health, statistics, electrical engineering, or a related field.

Strong candidates will have experience in one or more of the following areas:

  • Large language models, AI agents, or tool-using AI systems
  • Natural language processing, machine learning, or deep learning
  • Healthcare AI, clinical NLP, EHR data, medical imaging, or biomedical data science
  • Strong programming skills and a track record of research publications

How to Apply

Interested candidates should email their CV to jyang66#*#bwh.harvard.edu (replace #*# with @) with the subject line “Postdoc Application - Agentic AI”.

Applications will be reviewed on a rolling basis until the position is filled. Due to the high volume of applications, only shortlisted candidates will be contacted.