PeopleofSuperintelligence

Researcher

Brandon Anderson

Brandon Anderson is a machine-learning researcher whose work applies symmetry-aware neural networks to graphs, molecules and particle physics. He earned a PhD at the University of Maryland under Victor Galitski in 2011 and worked with Charles Clark at the Joint Quantum Institute before joining the University of Chicago as a postdoctoral scholar. In 2018, he coauthored graph-learning work with Risi Kondor and presented force-field research at the APS March Meeting. He coauthored Cormorant in 2019, ATOM3D and a Lorentz-equivariant particle-physics network in 2020, and an NMR prediction study with University of Chicago and Atomwise affiliations in 2021; ATOM3D received NeurIPS’s Datasets and Benchmarks Award. As of October 2026, he is a Staff Scientist in Machine Learning at Atomic AI.

Now at
Atomic AI

Timeline

  1. 2011

    A PhD at Maryland

    In 2011, he earns a PhD at the University of Maryland under Victor Galitski.

  2. 2018

    Postdoctoral research in Chicago

    Before moving to Chicago, he works with Charles Clark as a postdoctoral researcher at the Joint Quantum Institute. In 2018, he is a postdoctoral scholar at the University of Chicago, where he works with Risi Kondor on machine learning for physical systems. He coauthors “Covariant Compositional Networks for Learning Graphs” and presents “Learning Force Fields using Covariant Compositional Networks” at the APS March Meeting in March 2018.

  3. 2019

    Cormorant molecular networks

    In 2019, he coauthors Cormorant, a rotationally covariant neural network for learning molecular potential-energy surfaces.

  4. 2020

    ATOM3D molecular benchmarks

    In 2020, he coauthors ATOM3D, a collection of benchmark datasets for machine learning on three-dimensional molecular structures across several biomolecule classes.

  5. 2020

    Lorentz-equivariant particle networks

    In 2020, he coauthors “Lorentz Group Equivariant Neural Network for Particle Physics,” a model tested on classification of top-quark decays using jet constituents’ energy-momenta.

  6. 2021

    A community-powered NMR search

    In 2021, he coauthors “A community-powered search of machine learning strategy space to find NMR property prediction models,” with affiliations at the University of Chicago and Atomwise. The work uses a three-month Kaggle competition that receives 47,800 model predictions from 2,700 teams in 84 countries.

  7. 2021

    A NeurIPS datasets award

    NeurIPS gives ATOM3D the 2021 Datasets and Benchmarks Award; Anderson is one of its coauthors.

  8. As of October 2026

    Staff Scientist at Atomic AI

    As of October 2026, he is a Staff Scientist in Machine Learning at Atomic AI.

Career

  1. NowAtomic AIStaff Scientist in Machine Learning
  2. 2021Atomwise
  3. University of MarylandPostdoctoral Researcher
  4. University of ChicagoPostdoctoral Scholar

Education

  1. University of MarylandPhD

From the biography.

Videos

YouTube videos in which Brandon Anderson speaks or appears, newest first. A model chose them from YouTube search results. Key moments are from summaries that Gemini wrote. List updated 21 October 2026.

  1. From Wet Lab to RL Env: 10,000 Drug-Discovery Campaigns in a Weekend — Ian Quigley, Leash BioLatent Space · 14 October 2026 · 1 h 50 min
  2. Why AlphaFold Didn't Solve Protein Folding — Pushmeet Kohli, Google DeepMind & Sal Candido, BiohubLatent Space · 10 October 2026 · 33 min

    Key moments 0:22 While public narrative suggests "protein folding is solved,"… 12:03 AlphaFold 2 integrated domain knowledge from biophysics and… 19:09 When asked what single resource could accelerate structural… 20:47 However, achieving true 10x acceleration in clinic-ready therapies… 29:12 Both panelists agree that AI is already embedded…

  3. 🔬 From Red Teaming GPT-4 to Automating Drug Discovery: The Future of AI in Science — Andrew WhiteLatent Space · 28 January 2026 · 1 h 14 min

Video data from YouTube API Services. By watching you agree to the YouTube Terms of Service. How we use YouTube data.

  1. People shaping AI work at a median of 3 organizations over a career: 3 for university starters and institute and lab starters, versus 2 for company startersIncludes University of Maryland. Across 6,853 people shaping AI with a dated work role, we estimate a median of 3 parent organizations over a career (mean 3.6), comparing role groups, starting sectors and starting decades from the 1950s to 2020–2026.
  2. The median h-index is 48 at universities and 14 at frontier AI labsIncludes University of Chicago. The median h-index is 48 at universities and 14 at frontier AI labs. We compare publishing careers, recent citations, dual appointments and job moves across 2,420 university researchers and 308 frontier-lab researchers.
  3. The Massachusetts Institute of Technology trained or employed 44 of the 187 AI major-prize winners, more than any other universityIncludes University of Chicago. The Massachusetts Institute of Technology trained or employed 44 of the 187 AI major-prize winners, more than any other university. We compare doctorate and 5+ year employment links, career timing and current workplaces for 187 major-prize and 1,111 best-paper winners.
  4. More people shaping AI studied at Massachusetts Institute of Technology than at any other institutionIncludes University of Maryland. We estimate where the people shaping AI studied and where their careers led. Massachusetts Institute of Technology leads with 467 former students, including 291 recorded doctorates.

Colleagues

People named in this biography, and people with dated positions at the same organization in the same years.

Sources and credits

Photo: We have no published photo of Brandon Anderson yet. Send us a free-licensed photo.

  1. Brandon Anderson - Home jfi.uchicago.edu. Checked 21 October 2026.
  2. Research Group - Professor Victor Galitski terpconnect.umd.edu. Checked 21 October 2026.
  3. Colloquium: Brandon Anderson, University of Chicago | Physics - Lehigh University Events Calendar eventscalendar.lehigh.edu. Checked 21 October 2026.
  4. Machine Learning in Condensed Matter Physics II - APS March Meeting 2018 meetings-archive.aps.org. Checked 21 October 2026.
  5. Covariant Compositional Networks For Learning Graphs arxiv.org. Checked 21 October 2026.
  6. Cormorant: Covariant Molecular Neural Networks arxiv.org. Checked 21 October 2026.
  7. ATOM3D: Tasks On Molecules in Three Dimensions arxiv.org. Checked 21 October 2026.
  8. Paper page - ATOM3D: Tasks On Molecules in Three Dimensions huggingface.co. Checked 21 October 2026.
  9. Lorentz Group Equivariant Neural Network for Particle Physics proceedings.mlr.press. Checked 21 October 2026.
  10. A community-powered search of machine learning strategy space to find NMR property prediction models | PLOS One journals.plos.org. Checked 21 October 2026.
  11. NeurIPS 2021 Awards neurips.cc. Checked 21 October 2026.
  12. About Us – Atomic AI atomic.ai. Checked 21 October 2026.
  13. PhDs Awarded physics.umd.edu. Checked 21 October 2026.