Shivansh Rao
rao.shivansh570@gmail.com
Biography
I am a Senior Research Engineer and Applied ML Lead at Glass Imaging, where I own the end-to-end ML R&D cycle — from concept to real-time, on-device deployment — for smartphone imaging, spanning Neural ISP design (RAW→RGB), HDR/SDR burst restoration, RAW super-resolution, and image registration. I led the ML development for the company's first shipped customer product, training the on-device RAW burst pipeline now running in production smartphones, and act as the technical ML point of contact across OEM programs. Previously, I was a Senior ML Engineer in XR R&D at Qualcomm Technologies (San Diego, CA), designing hardware-accelerated computer-vision IP for feature detection, visual SLAM, and 3D reconstruction shipped across automotive, smartphone, and AR/VR products. I earned my MS from Penn State University, focusing on computer vision and 3D vision under Prof. C. Lee Giles and Prof. Dan Kifer. I received my BS in ECE from Delhi College of Engineering (2019), advised by Prof. Rajesh Rohilla. During my undergraduate studies, I was a visiting researcher at the University of Manitoba (Prof. Yang Wang) and a research intern at IIT Kanpur (Prof. Vinay Namboodiri) and IIT Delhi (Prof. Madasu Hanmandlu). My work spans publications at CVPR, ECCV, and ACM-MM, and 7 published U.S. patent applications.
.png)
.png)
.png)
