Meet Shah

I am an engineer working on autonomous systems at Google DeepMind. I have several years of experience in developing and scaling ML systems with a penchant for speeding and compressing models. Before starting at DeepMind, I enjoyed scaling perception systems at Waymo.

I graduated from IIT-Bombay where I worked at Vision, Graphics and Imaging Lab (ViGIL) on semi and weakly supervised deep learning methods. After graduation, I had the pleasure of working at Facebook AI Research as part of the inaugural FAIR AI Residency Program with Devi Parikh.

I promote Open Source Software and keep making my little contributions as and when time permits. My publications can be found on Google Scholar.

Selected Publications

Towards Conversational Medical AI with Eyes, Ears and a Voice

Preprint 2026 · [arXiv] [Scholar] [Blog]

LiRaNet: End-to-End Trajectory Prediction using Spatio-Temporal Radar Fusion

CoRL 2020 · [arXiv] [Scholar]

MS-Net: Mixed-Supervision Fully-Convolutional Networks for Full-Resolution Segmentation

MICCAI 2018 · Runners Up, Young Scientist Award · [arXiv] [Scholar]

Cycle-Consistency for Robust Visual Question Answering

CVPR 2019 · Oral · [arXiv] [Scholar]

Pythia: A Platform for Vision & Language Research

MLSys Workshop, NeurIPS 2018 · [arXiv] [Scholar]

Towards VQA Models That Can Read

CVPR 2019 · [arXiv] [Scholar]