cv
Contact Information
| Name | Jacob W. Toney |
| Role | PhD Candidate, Chemical Engineering & Computational Science, MIT |
| jwt@mit.edu | |
| jacob-w-toney | |
| Google Scholar | Jacob W. Toney |
Professional Summary
PhD candidate in Chemical Engineering and Computational Science at MIT working at the intersection of machine learning and quantum chemistry. Developing geometric deep learning models and large quantum chemical datasets to predict the structural, electronic, and chemical properties of transition metal complexes. Additional technical experience in quantum computing algorithms for chemistry (IBM Research) and large-scale operations engineering (SpaceX).
Education
-
2022 - 2027 Cambridge, MA
PhD, Chemical Engineering and Computational Science
Massachusetts Institute of Technology
Minor in Quantum Chemistry · Advisor: Prof. Heather J. Kulik
- Thesis: Accelerating Quantum Chemistry with Machine Learning for the Rational Design of Transition Metal Complexes
- Coursework: computational chemistry, advanced electronic structure theory, machine learning algorithms, ML for chemistry, matrix calculus for ML, diffusion models, generative AI and stochastic differential equations, numerical methods, Bayesian modeling and inference
-
2019 - 2021 Los Angeles, CA
MS, Chemical Engineering
University of Southern California
Research advisor: Prof. Shaama M. Sharada
- Thesis: Investigating the Mechanisms of C–H Activation with Enzyme-Inspired Molecular Catalysts (Awarded Best Research Paper)
-
2017 - 2021 Los Angeles, CA
BS, Chemical Engineering
University of Southern California
Minor in Materials Science · GPA 4.00
Experience
-
2023 - Cambridge, MA
Graduate Research Assistant
Kulik Group, MIT Department of Chemical Engineering
- Developed graph neural networks to predict organometallic bonding in transition metal complexes from ligand structure (PNAS), and extended the approach to dynamic coordination modes using ensemble learning (JACS).
- Co-led construction of BOS-TMC, the largest DFT dataset of experimentally characterized transition metal complexes in multiple charge and spin states (JCIM).
- Supported development and benchmarking of state-of-the-art generative transition state models (Nat. Comput. Sci.).
- Built ElemeNet, a unified machine learning framework for chemistry supporting E(3)-equivariant architectures with uncertainty quantification across the periodic table.
- Designed novel physics-based molecular fingerprints from spectral graph theory to encode 3D information while preserving permutation and E(3) invariance.
- Maintain the group HPC cluster and contribute to the open-source molSimplify structure generation package.
-
2026 - 2026 Yorktown Heights, NY
Algorithms and Applications Intern
IBM Research
- Developed wavefunction embedding schemes for simulating large molecular systems on quantum computers.
- Investigated fine-tuning generative models for protein structure prediction.
-
2021 - 2022 Hawthorne, CA
Operations Engineer
SpaceX
Full-time
- Led cross-functional cost-reduction campaigns to optimize Falcon 9 production.
-
2020 - 2020 Houston, TX
Process Engineering R&D Intern
ExxonMobil Research & Technology Development
- Developed computational tool for automated heat-exchanger design, reducing engineering labor hours by 10%.
-
2019 - 2021 Los Angeles, CA
Undergraduate Researcher
Sharada Group, USC Department of Chemical Engineering and Materials Science
- Performed DFT mechanistic studies of C–H hydroxylation by enzyme-inspired copper–oxygen complexes.
- Published in Catal. Sci. Technol. and recognized with departmental awards for best research paper and presentation.
Publications
- A full, up-to-date list — with abstracts, DOIs, and code — is on the publications page.
- Also indexed on Google Scholar and ORCID.
Honors and Awards
-
2026 Entalpic AI for Science Fellowship
Entalpic
-
2025 Leslye Miller Fraser and Darryl M. Fraser Fellow
MIT School of Engineering
-
2024 MathWorks Engineering Fellow
MIT Department of Chemical Engineering
-
2022 Alfred P. Sloan UCEM Fellowship
MIT School of Engineering
-
2021 Albert Dorman Valedictorian
USC Viterbi School of Engineering
-
2021 National Academy of Engineering Grand Challenges Scholar
USC Viterbi School of Engineering
-
2021 University Trustees Award
USC — awarded for perfect GPA
-
2021 Best Research Paper — *Bioinspired Catalysis of C–H Hydroxylation: A Computational Approach*
USC Viterbi School of Engineering
-
2021 Best Analytical & Expository Essay — *Engineering Ethics: Grand Challenges and Grander Responsibilities*
USC Viterbi School of Engineering
-
2021 Outstanding Chemical Engineering Student Award
USC Department of Chemical Engineering and Materials Science
-
2021 Best Research Presentation — *Investigating the Mechanisms of C–H Activation with Enzyme-Inspired Molecular Catalysts*
USC Department of Chemical Engineering and Materials Science
-
2019 Provost's Undergraduate Research Fellowship
USC (January 2019 – December 2020)
-
2017 Presidential Scholar
USC
-
2017 Latino Alumni Association Scholar
USC
Presentations
- International Conference on Quantum Chemistry, Berkeley, CA — Machine Learning Prediction of Structural and Electronic Properties of Transition Metal Complexes, poster. June 2026.
- Entalpic LeMaterial Reading Group, virtual — Exploring Structure, Properties, and Reactivity in Transition Metal Complexes with Deep Learning and Quantum Chemistry, invited talk. February 2026.
- AIChE Annual Meeting, Boston, MA — Graph neural networks for predicting metal–ligand coordination in transition metal complexes, talk in Data Science and ML Approaches to Catalysis: Catalyst Design and Discovery. November 2025.
- WATOC, Oslo, Norway — Graph neural networks for predicting metal–ligand coordination in transition metal complexes, talk in Chemical Structure and Reactivity: Analysis. June 2025.
- CECAM Frontiers of Computational Reaction Prediction, Chicago, IL — Graph neural networks for predicting metal–ligand coordination in transition metal complexes, poster. July 2024.
- USC ChE & Materials Science Research Symposium, Los Angeles, CA (virtual) — Investigating the Mechanisms of C–H Activation with Enzyme-Inspired Molecular Catalysts, recorded talk. February 2021. Awarded Best Research Presentation.
- AIChE Annual Student Conference, San Francisco, CA (virtual) — Computational Analysis of C–H Hydroxylation in Bio-inspired Monometallic Complexes, poster. November 2020.
- USC ChE & Materials Science Research Symposium, Los Angeles, CA — Computational Analysis of C–H Hydroxylation in Bio-inspired Monometallic Complexes, poster. March 2020.
- AIChE Annual Student Conference, Orlando, FL — Computational Analysis of C–H Hydroxylation in Bio-inspired Monometallic Complexes, poster. November 2019.
Teaching
- 5.698/10.637: Computational Chemistry (MIT) — Grader, graduate elective in chemical engineering and chemistry. Sep–Dec 2025.
- 10.34: Numerical Methods Applied to Chemical Engineering (MIT) — Graduate Teaching Fellow, graduate core course. Sep–Dec 2024. Instructor rating 6.5/7.
- 10.65: Chemical Reactor Engineering (MIT) — Grader, graduate core course. Feb–May 2024.
- 10.40: Chemical Engineering Thermodynamics (MIT) — Grader, graduate core course. Sep–Dec 2023.
Mentorship and Service
- David Sauer (Chemistry, Harvard University) — reparameterization of electronic structure methods for transition metal complexes.
- Zheming Zhang (Chemical Engineering, MIT) — benchmarking deep learning architectures for electronic property prediction in variable charge and spin states.
- Lauren Wright (Chemical Engineering, Louisiana State University) — designing new hydroformylation catalysts through mechanistic study and data science. Presented at the AIChE Annual Student Conference 2025; Awarded Third Place Poster.
- Sebastian Pujet (Chemical Engineering and Computer Science, Washington University in St. Louis) — active learning to optimize mechanochemical properties of transition metal complexes. Contributed to molSimplify 2.0, J. Chem. Inf. Model. 2026.
- President, USC AIChE Student Chapter. April 2020 – May 2021.
- President, USC Latino Alumni Association Scholar Committee. January 2019 – May 2021.
Skills
Machine learning: geometric deep learning (GNNs, E3NN), generative models (diffusion, flow-based), uncertainty quantification, active learning, Bayesian modeling and inference
Quantum chemistry: density functional theory (TeraChem, ORCA, Psi4, PySCF), post-Hartree–Fock methods, transition-state search, quantum computing and quantum algorithms
Scientific computing: Python, PyTorch, PyTorch Geometric, HPC cluster administration, multi-GPU training