PhD Student Bio

In July 2025, I will start as a relAI PhD student at Helmholtz Munich and the Technical University of Munich (TUM) as a member of the ELPIS lab, supervised by Dr. Vincent Fortuin. I aim to contribute to the reliable application of AI in science through better uncertainty quantification and robustness.

I am currently working as a research associate at the Professorship of Energy Management Technologies at TUM, conducting applied ML research. My work focuses on reliable wind power forecasting and developing software for more efficient and streamlined ML development in the energy research community. Before that, I studied mathematics at TUM, focusing on probability theory, statistics, and financial applications.

I strongly believe that Bayesian deep learning is a key approach for reliable AI for science. My PhD project aims to investigate how Bayesian principles can be applied safely in modern ML, how priors can be informed with previous knowledge, and how this leads to more reliable and data-efficient ML for scientific tasks.