Machine learning
for messy human text.
I build machine learning systems for medicine, language, and the spaces between research and practice.
About me.
I am a Data Scientist and PhD candidate at the Technical University of Munich, where I research Medical NLP at the Chair of Software Engineering for Business Information Systems (sebis).
My work sits at the intersection of information retrieval, synthetic data generation, and model evaluation, building systems that read, reason, and recommend across messy real-world text.
Nine years of programming, several first-author papers, one master's degree (1.2), and a stubborn belief that good engineering is what makes research useful.
Now.
Academic timeline.
PhD Research, Medical NLP
Technical University of Munich · sebisContinuing doctoral research with a focus on information retrieval, synthetic data, and evaluation of medical language models.
PhD Research, NLP
Ulm UniversityStarted doctoral research on advanced natural-language processing techniques for scientific and bibliographic text.
M.Sc. Computer Science (1.2)
Ulm UniversityThesis: "Retrieval Augmented Information Extraction: Enhancing Language Models with CRAWLDoc."
Student Research Assistant
Data Science groupCo-authored work on transformer-based short-text classification and other NLP topics.
B.Sc. Computer Science (1.3)
Ulm UniversityThesis: "Transformers are Short Text Classifiers."
Selected publications.
Synchronized live with DBLP, supplemented with manually curated entries.
Selected projects.
The toolbox.
Research
Models
Stack
Let's talk.
Open to connect. Best reached by email.