I am a Director, Research Scientist at Google DeepMind and lead the team that built the Reinforcement Learning from Human Feedback (RLHF) technology used in Bard, PaLM 2 (via Vertex AI, PaLM API, Duet AI), Gemini, Gemma, and various other Google products.
Since joining Google Brain, I worked on various problems in machine learning and artificial intelligence, including projects related to generative modeling, copmuter vision, reinforcement learning and representation learning. In my PhD studies at ETH Zurich, I investigated coresets - small summaries of large data sets with theoretical guarantees - and other sampling methods for large-scale machine learning. During that time I also held a Google PhD Fellowship.