I'm an assistant professor at Princeton University's Department of Astrophysical Sciences and the Center for Statistics and Machine Learning. I lead the Astro Data Lab, where we solve problems that hold back astronomy, and the Dynamical Learning Lab, where we model evolving systems, from nature to neural networks.

I create new techniques to discover the hidden state and the latent code of complex systems from empirical data. By embedding mathematical or physical structure in deep learning architectures, my group and I build probabilistic models of hidden worlds: My research is funded by NSF and NASA to build the best models of distant galaxies by combining data from the three flagship observatories Rubin, Euclid, and Roman; by the W. M. Keck Foundation to discover Earth-like exoplanets; by Schmidt Sciences to find out how to best use the cutting-edge spectrograph PFS; by the HydroGEN collaboration to reveal the state of groundwater across the entire continental United States and build a digital twin that predicts droughts, wildfire conditions, and the availability of drinking water. Head over to my publications if you want to know more.

I'm also a passionate educator and mentor. I teach courses on computational methods, statistics and probabilistic machine learning. And I care deeply about the development of the natural sciences in the AI era. You can find more on my position from my public talks.