I work at the intersection of privacy and machine learning, focusing on making AI systems more private and trustworthy. Currently leading research at Fraunhofer AISEC and pursuing a PhD at Freie Universität Berlin, I combine academic insights with practical applications.
I regularly speak about privacy-preserving ML, practical privacy engineering, and the intersection of AI and society. Recent topics include differential privacy in practice, private synthetic data generation, and secure ML systems.
Google Research @ Munich
> Presented results from our AAAI-25 paper 'Differentially Private Prototypes for Imbalanced Transfer Learning'.
Cosmo Consult
> Presented practical applications of privacy-preserving AI techniques in real-world business scenarios.
Health & Law Network Berlin
> Presented on the use of synthetic data generation techniques to protect patient privacy.
Conducting research in privacy-preserving machine learning and developing practical solutions for secure AI applications.
Pursuing doctoral research in privacy-preserving machine learning and their real-world applications.
A startup focused on innovating the apartment search and rental process through technology and user-centric design.
Led a research project on private machine learning for imbalanced transfer learning.
Automated data processing using Python, IEC61850 substation automation, cluster management, ISO9001 quality management.
Aggregated hydraulic power plants and modelled coupled power and heat (CPH) systems.
Product lifecycle management of electronics for medical devices.
Assisted in various projects regarding the european energy market, processing using MATLAB.
Supervision of students and examination of software projects.
Specialized in electrical power systems and computer engineering.
Developed ML models for renewable energy forecasting systems.