About Me

I am interested in understanding multimodal data, particularly genomic data, through high-dimensional statistics, machine learning, and AI-driven data science. More recently, my work has expanded toward exploring how AI agents can encode human approaches to measuring and modeling complex biological systems, and how these agents can, in turn, deepen our understanding of biology.

Working with university PIs who advance methodology and with national-lab teams confronting real-world datasets showed me that a broad community spanning academia and beyond is driving progress in tackling the scale, diversity, modalities, and novelty of modern biomedical data. I hope to contribute to this effort by developing agentic systems, alongside computational and analytical approaches, that uncover underlying structure.

I value interpretability and insights drawn from diverse domains, especially as we consider how data science will evolve over the next fifty years. In the long term, health data sits at the frontier of integrating with the physical world, and designing questions at this scale requires methodological rigor along with openness to understanding and communicating across fields.