I am currently in my final year as a Computational Linguistics B.A. student at Heidelberg University, where I also work as an undergraduate research assistant in the Department of German Language and Literature, applying computational linguistic methods in interdisciplinary digital humanities projects spanning automatic analysis of moralizing practices, political science, psychology, and other fields. My academic training combines Computational Linguistics, Natural Language Processing, and Machine Learning.

My primary research focus is interpretability in NLP, motivated by broader questions of AI safety. I am particularly interested in extending this work to vision-language models.