I'm a Senior Staff Research Scientist at Google DeepMind, where I'm part of the Gemini team, pushing the frontier of multimodal intelligence with a focus on video understanding. My work at Google has centered on Generative AI and large-scale vision systems. Before joining Google, I earned my PhD from ETH Zurich, specializing in efficient and theoretically grounded data selection and clustering algorithms. I also had the privilege of serving as an Area Chair for both NeurIPS and ICLR conferences prior to 2025.