Simon Batzner



E-Mail: echo "moc.liamg@renztabnomis" | rev

Research Interests

My interests lie at the intersection of Deep Learning and Physics, in particular on the role of structure and symmetry in Deep Learning.



I am a Research Scientist at Google DeepMind in San Francisco. I recently defended my PhD from Harvard University, where I spent 4 years in the group of Boris Kozinsky as well as six months at Google Brain working with Ekin Dogus Cubuk. Prior to Harvard, I obtained a Master's from MIT, where I wrote a thesis on equivariant neural networks. During my undergrad, I spent a year in Los Angeles, working on the NASA mission SOFIA, where I wrote software for analyzing telescope data and used ML to model the dynamics of piezolelectrics. I obtained my Bachelor's from the University of Stuttgart, Germany. I am originally from a small, but beautiful town a few minutes from the Bavarian Alps.



Here is a link to my Google Scholar.


Here is a link to my Linkedin.

Invited talks


During my PhD I published two codes for the NequIP and Allegro potential. Both are public on my PhD group's Github. If you have questions, please reach out to the current developers on the GitHub, they are happy to help: Both of these also come with a LAMMPS pair_style, written by my brilliant former labmate Anders Johansson, which can be found here:

Referee Activity

Reviewer for Nature Computational Science, NeurIPS, ICML, Nature Communications, Communications Chemistry, Journal of Chemical Theory and Computation, ACS Nano


Last updated: 05/2023