About

I’m a dual-background researcher who was appointed as Tenure-track Assistant Professor for medical AI at ETH Zurich (see announcement). Prior to this, I was a postdoctoral researcher at Stanford University in the group of Prof. Jure Leskovec. Previously, I completed my PhD at ETH Zurich in the Machine Learning and Computational Biology Lab of Prof. Karsten Borgwardt, and my MD and medical training at the University of Basel. Here, you can find my CV.
During my PhD, I developed machine learning models for medical time series and developed methods for representation learning, spiked with topological data analysis. During my postdoc at Stanford, I have been exploring novel frontiers of medical AI and medical foundation models involving zero-shot and few-shot learning, knowledge injection, multimodal medical reasoning.
My current research focuses on developing and evaluating flexible and reusable pre-trained AI models, including language models, vision-language models, and AI agent systems for various medical and biomedical use-cases.
Concretely, my vision is to develop generalist models for medicine (see figure excerpt below), i.e. large, pre-trained medical foundation models that can flexibly ingest multiple modalities, solve dynamically specified tasks (zero-shot or few-shot) and reason over (and retrieve from) structured and editable biomedical knowledge sources.