I am a Research Scientist at Google DeepMind in Zurich, specializing in post-training, model souping, and data-centric machine learning for large foundation models. I study how training data and weight-space geometry shape model behavior. My goal is to develop scalable methods for understanding the influence of data on generative AI systems and for efficiently combining, editing, and adapting pretrained models across tasks.

Before joining Google DeepMind, I completed my PhD in Computer Science at École Polytechnique Fédérale de Lausanne (EPFL), under the supervision of François Fleuret and Pascal Frossard. During my PhD, I completed two research internships at Google DeepMind, working on LLM post-training and text-to-image generation. Before coming to Switzerland, I completed my undergraduate studies in Electrical and Computer Engineering at the National Technical University of Athens (NTUA) in Greece, where I conducted my thesis at the CVSP lab under the supervision of Petros Maragos.

Download my resumé .