I’m a PhD student in the International Max-Planck Research School for Intelligent Systems (IMPRS-IS), co-supervised by Enkelejda Kasneci and Seong Joon Oh at the University of Tübingen.

My goal is making machine learning more trustworthy by delivering pretrained uncertainty estimates along with each prediction. To this end, I’m developing probabilistic embeddings that represent a model’s uncertainty directly in its embedding space. I love to understand and prove things first from a theoretical perspective first (like MCInfoNCE) and then scale them to large datasets as in the new URL benchmark.

I received my BSc (2018) and MSc (2021) in Statistics with distinction at TU Dortmund University where I focussed on probabilistic modeling and machine learning. In 2019, I was a research intern at BMW Group, Munich.