I work where algorithms, cells, and experiments meet.

My training began in biological science and pharmacology, then expanded through biotechnology, genomics, statistics, and computational biology. That path shaped how I approach model development: biological context and experimental constraints should influence the algorithm from the beginning.

At UCSF, I develop methods for learning coherent cell-state landscapes and apply them to development, cancer, immunology, and perturbation response. I also build open-source software and mentor researchers working across dry-lab computation and wet-lab experimentation.