About Me

As a data scientist with expertise in machine learning, scalable data systems, and signal processing, I thrive at the intersection of cutting-edge technology and complex problem-solving. Recently, I have been focusing on developing deep learning models for denoising 3D imaging data with minimal photon counts, leveraging architectures like 3D U-Nets and Noise2Noise training. This work required designing efficient data pipelines capable of processing billions of events and is being prepared for publication.

My professional journey includes contributions to diverse interdisciplinary projects. At DESY, I built a modular Python-based toolbox to process high-throughput data streams, enabling scalable and efficient analysis. Earlier, at Hörtech/Hearing4all, I contributed to real-time acoustic signal processing algorithms and developed tools to optimize algorithm deployment, bridging the gap between research and real-world applications.

Academically, I hold a Master’s degree in Data Science from RWTH Aachen, providing a comprehensive foundation in the theoretical, mathematical, and applied aspects of data science. My coursework ranged from theoretical topics like convex optimization and statistical learning theory to practical tools like image processing and big data tools. Before that, I earned a Bachelor’s degree in Engineering Physics, where I explored quantum mechanics, solid-state physics, and applied engineering topics. A semester exchange at the Technical University of Denmark further enriched my understanding of scientific innovation and engineering.

Beyond my technical expertise, I am passionate about using data science responsibly to address real-world challenges, from advancing scientific research to building scalable, ethical solutions. My experience spans designing algorithms for noisy, high-dimensional datasets, building modular software systems, and collaborating across diverse teams to achieve meaningful results.