I did my PhD at the Laboratory for Physical Chemistry (now: Institute of Molecular Physical Science) at ETH Zurich. I worked in the research group of Prof. Markus Reiher. I developed procedures to apply methods from the field of machine learning and artificial intelligence to theoretical chemistry. My first paper applies Gaussian process regression and Bayesian sampling to dispersion interaction between organic compounds to yield more accurate results as well as streamline the pipeline of starting new reference calculations for compounds too dissimilar to the training set.

Before, I worked at MIT under Prof. Heather J. Kulik for my Master thesis, on transition metal complexes for multifidelity machine learning. The work was published and won an MSDE award. Another collaboration was published and a follow up to my thesis.

From 2013 to 2018 I studied Interdisciplinary Science at ETH Zurich with a major in Computational and Physical Chemistry.

• 06/2026 Generative exploration of chemical reaction networks. CNRS / Université de Lorraine, Nancy (invited)
• 12/2025 How simple can you go? Machine learning molecular dynamics with minimal physical constraints. Pacifichem 2025, Honolulu
• 10/2025 Machine learning and AI for the sciences: toward understanding. Latvian Institute of Organic Synthesis, Riga (invited)
• 09/2025 Chemical reaction network exploration with diffusion probabilistic models. Young WATOC, Oslo; DTU Energy, Copenhagen (invited)
• 08/2025 Generative computational chemistry: From reverse diffusion to XAI. University of Basel (invited)
• 12/2024 Accelerating computational chemistry with machine learning. University of Freiburg (invited)