Dave Van Veen

Multimodal AI Researcher | Stanford PhD

prof_pic.jpg

I build AI systems that advance medicine at scale.

Currently, I'm a Principal AI Scientist at HOPPR, where I develop multimodal models in radiology. My work spans data pipelines, model training, and production engineering. I thrive when collaborating across disciplines to deliver AI that actually works.

Aside from building, I seek adventure—like bikepacking across Mexico—and solitude in nature via reading, surfing, and trail running with my dog.


bio

Dave earned his PhD in Electrical Engineering (EE) from Stanford under Akshay Chaudhari and John Pauly, where he developed algorithms for computational imaging and foundation models for medicine. He published 15+ papers (2000+ citations) across Nature, Nature Medicine, CVPR, ACL, et al.

Previously, Dave was a research scientist at a Bay Area start-up and Stanford's AIMI Center. He earned his MS at the University of Texas conducting machine learning research under Alex Dimakis and Sriram Vishwanath. Dave also served as a Data Science for Social Good fellow in London. During his BS in EE at the University of Wisconsin, he founded Badgerloop, a 150-person team that built a hyperloop pod for SpaceX.

news

Mar 2026 Merlin, our 3D abdominal CT foundation model, is published in Nature.
Jan 2026 Shared a blog post on my workflow with agentic coding: a fundamental shift in engineering that has only just begun.
Dec 2025 Wrote a personal essay about my mother’s childhood growing up on the farm: a way of life that is now hard to imagine.
Sep 2025 Our team at HOPPR introduces RadEval, an open-source framework for evaluating AI-generated text in radiology.