I'm a senior software engineer in Google A.I. Perception interested in machine learning and computer vision. My current work focuses on automating neural network architecture design by allowing networks to adjust their structure seamlessly during training. My work spans a wide range of computer vision problems such as image classification, semantic segmentation, and metric learning. My research has been published in top-tier conferences such as CVPR, ECCV, and SIGGRAPH. Models using my work were deployed in major Google products such as Google Photos, Pixel Phone Camera, and Street View. I have a PhD in Computer Science from Carnegie Mellon University. I was lucky to be co-advised by Yaser Sheikh and Takeo Kanade. More information at my Google Scholar Profile.