Work With Me

I am always excited to work with curious, motivated people — students, engineers, clinicians, and researchers — on AI for healthcare. My current work centers on three directions: multimodal foundation models and agents for medicine, rigorous evaluation environments and benchmarks for medical AI, and bridging AI to patients, clinicians, and health systems. You can read more about each on my home page.

Prospective Students

Undergraduate and graduate students (Yale, Harvard, Stanford, MIT). The best way to work with me is through the AI track of the Medical AI Bootcamp: a closely mentored, publication-oriented research experience. You should have solid machine learning foundations, be comfortable with Python and PyTorch, and be able to commit meaningful weekly time across at least two semesters.


Students elsewhere. I welcome remote collaborators and visiting PhD students from outside these institutions when there is a strong match with my research directions — typically students with prior research experience and demonstrated engineering ability. If that sounds like you, welcome to reach out and show what you have built or published.


Students interested in a PhD. If you are considering a PhD in medical AI, I am happy to chat about directions and how to build a competitive profile. Prospective PhD students should apply through the Yale Biostatistics PhD program.

Clinical Experts

Clinical insight is what keeps medical AI honest. If you are a physician interested in doing hands-on AI research, the Medicine track of the Medical AI Bootcamp is open to MDs and equivalent degree holders worldwide.


I am also glad to collaborate with clinicians on dataset curation, clinically grounded evaluation of AI systems, reader studies, and deployment-oriented projects at the interface of AI and clinical workflows.

Research Collaborators

I welcome collaborations with academic labs, health systems, and industry teams on shared research problems — particularly around building and evaluating multimodal medical foundation models, simulation-based evaluation of clinical AI (see our Clinical Environment Simulator perspective in Nature Medicine), and patient- and clinician-facing AI systems.

How to Reach Out

Email me at luyangluoteam@gmail.com with "[Join]" in the subject line, and include:


  • Your CV (and transcript, if you are a student)
  • A few sentences on why you are interested in medical AI
  • Links to anything that shows your work: papers, code, projects