Senior Research Scientist at Google Brain.
After graduating from the Moscow State University he was a postdoc at the University of Freiburg working on self-supervised learning, image generation as well as motion and 3D structure estimation (FlowNet, DeMoN). In 2017 he joined Intel Visual Computing Lab and worked on applications of deep learning to sensorimotor control, including autonomous driving (CARLA simulator) and robotics (drone racing, learning to walk). Since April 2019 he is with Google Brain in Berlin. His current research interests are focused on learning representations for downstream tasks such as recognition or control.