I am a Senior Research Scientist at Google DeepMind, Mountain View, CA. My research aims at developing deep and reinforced AI systems that are scalable and feasible for learning from the real world. My recent works including automatic neural network training systems and reinforcement learning based visual navigation in Google Streetview and Google Earth. Sitting at Google Headquarters, I also work closely with many engineering teams to land AI technologies into Alphabet products. A recent collaboration where I was heavily involved is applying Population Based Training into Google's self-driving cars. I am also an AI coach in Google Launchpad Accelerator to help non-profit organizations apply AI techniques to address environmental problems such as climate change.