Tobias Braun

I am an ELLIS PhD Candidate at the Technical University of Darmstadt (Multimodal AI Lab, Prof. Marcus Rohrbach) and currently a visiting researcher at UCL's Systems Security Lab (Prof. Lorenzo Cavallaro). My research lies at the intersection of multimodal AI, robustness, and security. I am interested in understanding how increasingly capable AI systems can fail, be manipulated, or behave unexpectedly — and how we can design safeguards that make them more trustworthy and aligned with human interests.

I hold an M.S. in Operations Research from Columbia University and a B.S. in Industrial Engineering from KIT. Before starting my PhD, I worked as an independent ML engineer, conducting more than 60 workshops that helped organizations adopt AI in practice. My long-term ambition is to contribute to the development of safe and beneficial artificial intelligence while strengthening scientific collaboration across Europe.

Having lived, studied, and worked in several countries, I enjoy connecting people, ideas, and disciplines. Outside research, I am an avid chess player, traveler, writer, lifeguard, and outdoor enthusiast.