I am currently a senior research scientist at Google DeepMind in London working on AI privacy, safety and trustworthiness in the context of frontier model applications.
Previously, I was a senior lecturer at the Technical University of Munich (TUM) leading the Privacy-Preserving and Trustworthy Artificial Intelligence research group at the Institute for Artificial Intelligence in Medicine and the Reliable AI research group at Helmholtz Munich.
I completed my post-doc in Artificial Intelligence with Professor Daniel Rueckert at the Department of Computing at Imperial College London.
Before dedicating myself to full-time AI research, I obtained my specialist diagnostic radiologist board certification at the Institute for Diagnostic and Interventional Radiology at TUM, my medical degree from LMU Munich and my Master's Degree in Health Business Administration from FAU Nuremberg.
My research at TUM and Helmholtz Munich focused on the following topics:
Previously, I was a senior lecturer at the Technical University of Munich (TUM) leading the Privacy-Preserving and Trustworthy Artificial Intelligence research group at the Institute for Artificial Intelligence in Medicine and the Reliable AI research group at Helmholtz Munich.
I completed my post-doc in Artificial Intelligence with Professor Daniel Rueckert at the Department of Computing at Imperial College London.
Before dedicating myself to full-time AI research, I obtained my specialist diagnostic radiologist board certification at the Institute for Diagnostic and Interventional Radiology at TUM, my medical degree from LMU Munich and my Master's Degree in Health Business Administration from FAU Nuremberg.
My research at TUM and Helmholtz Munich focused on the following topics:
- Privacy-preserving AI with a focus on Differential Privacy and its applications to deep learning
- Biomedical applications and deployments, especially in medical imaging
- Trustworthy AI (Explainability, Fairness, Alignment)
- AI security and attacks against machine learning models
- Memorisation and training dynamics of neural networks
- Probabilistic machine learning techniques
- Federated learning
- Geometric deep learning and graph neural networks