Matt Johnson is a research scientist at Google Brain interested in software systems powering machine learning research. When moonlighting as a machine learning researcher, he works on composing graphical models with neural networks, automatically recognizing and exploiting conjugacy structure, and model-based reinforcement learning from pixels. Matt was a postdoc with Ryan Adams at the Harvard Intelligent Probabilistic Systems Group and Bob Datta in the Datta Lab at the Harvard Medical School. His Ph.D. is from MIT in EECS, where he worked with Alan Willsky on Bayesian time series models and scalable inference. He was an undergrad at UC Berkeley (Go Bears!).