cv
General Information
| Full Name | Zachary W. Ulissi |
| Date of Birth | 1987 |
| Languages | English |
Experience
-
2023-present Research Scientist
Meta Fundamental AI Research (FAIR) - AI for chemistry and catalysis
-
2022-present (on leave) Associate Professor of Chemical Engineering
Carnegie Mellon University - Machine learning for computational chemistry
- Engineering and discovery of catalysts and inorganic materials
-
2017-2022 Assistant Professor of Chemical Engineering
Carnegie Mellon University - Machine learning for computational chemistry
- Engineering and discovery of catalysts and inorganic materials
-
2015-2017 Postdoctoral Scholar
Stanford University - Postdoc with Jens Nørskov in computational catalysis
Education
-
2015 PhD
Massachusetts Institute of Technology - Simulations and theory to describe carbon nanotube devices and sensors
- Systems engineering and parameter estimations for nanotube simulations
-
2010 M.A.St.
Churchill College, Cambridge, UK - Applied math and fluid dynamics courses.
- Research with Raymond Goldstein
-
2009 B.E/B.S.
University of Delaware - B.E. in Chemical Engineering
- B.S. in Physics
Open Source Projects
-
2020-now Open Catalyst Project
- The Open Catalyst Project builds open datasets and machine learning models to accelerate catalyst simulations.
Honors and Awards
-
2022 - Dean's Early Career Fellow (CMU Engineering Award)
-
2021 - G.T. Ladd Research Award
-
2020 - 3M Non-Tenured Faculty Award (NTFA)
- ACS Petroleum Research Fund (PRF) doctoral new investigator
-
2019 - Scott Institute for Energy Innovation Fellow
-
2010-2014 - DOE CSGF Fellow
-
2009-2010 - NSF GRFP Fellow
Academic Interests
-
Catalyst modeling and discovery
- Use of DFT to predict activity, selectivity, stability
- Active learning methods to systematically discover new catalysts
- Matching high-throughput calculations and experiments
- Electrochemical (CO2RR, HER, OER, ORR) and thermal catalysis (especially selective catalysis)
-
Artificial Intelligence / Machine Learning
- Large graph neural networks to predict simulation data
- Fine-tuning and active learning to accelerate
- Uncertainty quantification
- Embedding of ML models in heuristic optimization systems
-
Nanotechnology
- Carbon nanotube devices and sensors
- Interfacial phenomena
- Classical molecular dynamics simulations
Other Interests
- Hobbies: Cycling, cooking, traveling, outdoors, hiking