Eric Boittier, Ph.D.
Scientific Software Architect – Deep Learning Applications
Location: Arlesheim, BL 4144
Phone: +41 76 234 35 81
Email: eric.boittier@icloud.com
Languages: English (native), German (B2)
I build machine learning methods and scientific software for chemistry, molecular simulation, and graph-structured data. Public profiles: GitHub, Google Scholar, LinkedIn.
Experience
- 2020–2026: Researcher, University of Basel (Basel, CH). Deep learning on graph chemistry data, including models for physical simulation and electrostatics; first place in HYDRA Spectroscopy Prediction Challenge; peer reviewer for Journal of Chemical Physics.
- 2019–2020: Research Assistant, Translational Research Institute (Brisbane, AU). Small-molecule and biomolecular modeling with Schrödinger and OpenMM; collaborative end-to-end data science workflows in Python and R.
Skills
- Programming: Python, Julia, R, Fortran, C++, OpenMPI, CUDA
- Machine Learning: JAX, TensorFlow, PyTorch, scikit-learn, NumPy
- DevOps: Git, CI/CD, Docker
- Data Science: SQL, Polars, Pandas
Invited Technical Talks
- 2024: Bridging Machine Learning Force Fields with Anisotropic Electrostatic Models, Swiss Chemical Society Machine Learning Group (Lausanne, CH)
- 2025: Mixing Machine Learned and Empirical Energy Functions, apoCHARMM Meeting NIH (Boston, US; Online)
Open Source
- Community-driven contributions at
@EricBoittier - RDKit bug fixes across C++ and Python bindings, including merged PR 7811
- OpenCV + SQL tooling for inventory tracking
Education
- Ph.D. in Chemistry, University of Basel (2020–2025). Thesis: Molecular Deep Learning for Quantitative Simulations and Electrostatic Models.
- Bachelor of Advanced Science in Chemistry, University of Queensland (2015–2020). Thesis: Development of Computational Tools for the Rational Design of Glycosaminoglycan Mimetics.
Papers
- Boittier, Eric and Toepfer, Kai and Devereux, Mike and Meuwly, Markus, Kernel-based minimal distributed charges: a conformationally dependent esp-model for molecular simulations, Journal of Chemical Theory and Computation, 2024. DOI: 10.1021/acs.jctc.4c00759
- Vazquez-Salazar, Luis Itza and Boittier, Eric and Unke, Oliver and Meuwly, Markus, Impact of the characteristics of quantum chemical databases on machine learning prediction of tautomerization energies, Journal of Chemical Theory and Computation, 2021. DOI: 10.1021/acs.jctc.1c00363
- Boittier, Eric and Tang, Yat Yin and Buckley, McKenna E. and Schuurs, Zachariah P. and Richard, Derek J. and Gandhi, Neha S., Assessing molecular docking tools to guide targeted drug discovery of cd38 inhibitors, International Journal of Molecular Sciences, 2020. DOI: 10.3390/ijms21155183
- Kaeser, Silvan and Boittier, Eric and Upadhyay, Meenu and Meuwly, Marky, Transfer learning to ccsd(t): accurate anharmonic frequencies from machine learning models, Journal of Chemical Theory and Computation, 2021. DOI: 10.1021/acs.jctc.1c00249
- Boittier, Eric D. and Burns, Jed M. and Gandhi, Neha S. and Ferro, Vito, Glycotorch vina: docking designed and tested for glycosaminoglycans, Journal of Chemical Information and Modeling, 2020. DOI: 10.1021/acs.jcim.0c00373
- Boittier, Eric and Devereux, Mike and Meuwly, Markus, Molecular dynamics with conformationally dependent, distributed charges, Journal of Chemical Theory and Computation, 2022. DOI: 10.1021/acs.jctc.2c00693