I am a Member of Technical Staff at Microsoft AI working on multimodal perception and generation. Prior to this, I was a Senior Staff Research Scientist at Google DeepMind, where I worked on generative models for audio in the context of projects like NotebookLM Audio Overviews, Gemini Live and Lyria. Before that, I was a PhD student at ETH Zurich under the supervision of Prof. Andreas Krause. My PhD research focused on data summarization and adaptive data subsampling techniques for resource-constrained machine learning systems.