My work lies at the intersection of applied mathematics, scientific computing, and machine learning. I am particularly interested in how modern learning-based methods can be combined with classical numerical analysis and stochastic modeling to address large-scale, computationally challenging problems arising in the natural sciences.

My current research focuses on developing machine learning methods for scientific computing, with applications ranging from physics-informed learning and time-series prediction to computational chemistry. I am especially interested in multiscale systems, uncertainty quantification, and the design of computational tools that remain interpretable, robust, and grounded in first-principles modeling. I regularly share this work through my blog, Substack, and open-source projects.

Prior to transitioning to industry, I was a postdoctoral research fellow in the Department of Applied Mathematics and Statistics at Johns Hopkins University (JHU), with a secondary appointment in the Department of Chemical and Biomolecular Engineering. I worked under the supervision of dr. Ioannis Kevrekidis. Before moving to the United States, I earned my PhD from the University of Leuven (Belgium) in 2023. My professional background also includes experience as a software engineer at Facebook, where I worked on physics engines for virtual reality applications, as well as independent consulting work for energy companies.