My name is Joshua Yao-Yu Lin, and I am a Senior Machine Learning Scientist at Prescient Design, Genentech/Roche, where I develop machine learning approaches for drug discovery and protein engineering. My work sits at the intersection of machine learning and the natural sciences, with a particular interest in using deep learning to learn predictive and generative representations of complex scientific systems. Before my current role, I was a machine learning postdoc supervised by Prof. Kyunghyun Cho at Genentech.

I was born in South Africa, and I grew up in Taiwan. Before joining Prescient, I received my Ph.D. in physics at the University of Illinois at Urbana-Champaign, following an M.S. in physics at National Taiwan University and a B.S. in physics at National Tsing Hua University. Here’s my Resume.

During my Ph.D., my research centered on machine learning applications in physics and astrophysics, including Cosmology, Dark Matter, Neutrinos, Gravitational Lensing, and Supermassive Black Holes. I was also drawn to reinforcement learning and its potential connections to physics research. I was very fortunate to work with many Professors including Gil Holder, Charles Gammie, and Xin Liu at the University of Illinois, and I have been a member of the Event Horizon Telescope (EHT) collaboration since 2020. In spring 2021, I spent a semester at the CCA (Flatiron Institute, Simons Foundation) as a guest researcher, and in summer 2021 I was a research intern at Google Research, where I worked on multi-modality generative models.

Over time, my work has evolved from using machine learning to understand the natural world toward using it to design new biological molecules and therapeutics, with the broader goal of developing AI as a general-purpose tool for scientific discovery.