I’m a research scientist and a technical lead at Google. I work on computer vision and machine learning, in particular, on computational photography, image/video synthesis, optical flow and NeRF. Our research powers user facing features like the Cinematic Moments on Google Photos, and others coming up soon. I also publish papers and contribute deep learning models to the community.

Previously, I was a research scientist at NVIDIA Applied Deep Learning Research, led by Bryan Catanzaro, where I was a founding member. I served as a technical lead and co-founded a real-time graphics project that exploits the temporal domain to increase the performance of GPUs in video games, which culminated in the creation of DLSS 3.0. I’ve also pulished on topics spanning semantic segmentation, video prediction, image inpainting, and frame interpolation, that were featured in Fortune, Forbes, FastCompany, and have also been integrated into NVIDIA’s NGX Technology.

Prior to that, I was the lead inventor and researcher of the team that launched the Siemens FastSpine.v2 technology that automatically traces, detects and numbers the human spine in scoliotic patients in 3D CT/MRI images.

I received my PhD in Electrical Engineering from Vanderbilt University. My thesis was on computer vision algorithms for image-guided surgery techniques. I hold a MS degree in Computer Vision and Robotics, received from Heriot-Watt Univerisity.

My interests are on computer vision and machine learning, in particular, on their applications in real-life problems.