German Aerospace Center (DLR) Institute for AI Safety and Security

I am pleased to highlight my role as a research associate at the German Aerospace Center (DLR) in the Institute for AI Safety, specifically within the department of AI Safety and the team for Assessment and Testing Methods. My work in this position centers on advancing the safety of autonomous systems, particularly in the context of autonomous vehicles and driving functions. The rapid development of autonomous driving, driven by breakthroughs in deep learning, brings both opportunities and challenges. A key issue with these technologies is their black-box nature, which poses questions about their applicability in safety-critical domains such as traffic. In my research, I address these challenges by applying the principles of safety-by-design (ISO 26262) and safety assurance (ISO 21448), ensuring that risks are systematically considered and managed during the design and concept phases. My focus is on bridging the gap between engineering safety principles and AI systems, an emerging field known as AI engineering. Specifically, I model trade-offs between safety requirements and system functionality, contributing to the development of methodologies that ensure AI components comply with standards such as ISO 8800. This involves formulating safety arguments tailored to AI models and integrating them into the broader framework of system safety. This role has deepened my expertise in applying engineering principles to the complexities of AI and underscores my commitment to enhancing the safety and reliability of next-generation autonomous systems.

Research Assistant

I gained valuable experience as a research assistant for Prof. Rumpf at the University of Bonn, focusing on Deep Learning methods for point clouds. My work involved developing neural network-based implicit representations using the Ambrosio and Tortorelli theorem-based phase field approach, building on the foundation of my Master's thesis. I contributed to optimizing the existing framework, conducted experiments with different network architectures, and created test cases in 2D and 3D domains to validate the methodology. Programming was done in Python, with AI algorithms implemented using PyTorch. This role deepened my expertise in Deep Learning and computational mathematics, demonstrating my ability to solve complex challenges at the intersection of mathematics and technology.

Master of Science: Mathematics

I earned my Master of Science in Mathematics from Rheinische Friedrich-Wilhelms-Universität Bonn from October 2020 to November 2022, graduating with very good results. My thesis, Learning Geometric Phase Field Representations, supervised by Prof. Dr. M. Rumpf and Prof. Dr. T. Laux, marked a significant milestone. Pursuing a minor in Informatik expanded my knowledge of computer science, while mastering Deep Learning methods further enhanced my analytical and problem-solving skills in mathematics and technology.

Bachelor of Science: Mathematik

Pursuing a Bachelor of Science in Mathematics at the University of Bonn from September 2017 to September 2020 was a pivotal step in my academic journey. During this time, I deepened my understanding of mathematical concepts, honed my problem-solving skills, and explored my interest in economics through a minor. This experience provided a strong foundation for my academic and professional growth.