About

Neeraj Kulkarni is a highly skilled Software Engineer with over 10 years of relevant experience in the field. He is currently working as an SDE III (Staff/Tech Lead) for Amazon's Visual Search & AR (A9) group, where he designs and implements scalable backend systems for live and offline Augmented Reality experiences within Amazon mobile and web apps. Neeraj's work involves creating AR experiences that allow Amazon customers to visualize high-quality, realistic 3D models of hundreds of thousands of products right in their room, helping them virtually decorate their home and make buying decisions. Prior to his current role, Neeraj worked as a Staff SW Engineer/Tech Lead for the AR Interactions Team at Atheer, where he owned the whole stack and led the end-to-end development of a real-time natural hand gestures recognition system for android-based mobile AR platforms using single on-device RGB camera. He also built software infrastructure that allowed the team to train, evaluate, and compare modern object detection DNNs in a containerized distributed farm, choosing the best models in terms of both accuracy and inference speed. This resulted in an optimized model for on-device inference, which lies at the core of an on-device gesture recognition library that continually maps raw DNN outputs to rich, meaningful, and precise gestures reflecting user intentions in real-time. Neeraj's expertise also extends to end-to-end development of native libraries/services that perform 3D hand skeleton recognition and tracking to power a range of gestures running at 100 FPS for android-based mobile AR platforms, using an IR depth camera. He has integrated this technology into Android in two ways - direct integration into the OS to enable all standard gestures across the OS as well as an SDK allowing android apps to subscribe to additional gestures specialized for augmented reality platforms. Neeraj holds an M.tech. in Computer Science and Engineering from the Indian Institute of Technology, Delhi, and a B.E. in Information Technology from Vishwakarma Institute of Technology. His tech stack includes Android, Computer Vision, Mobile, ML, Object detection, Search, Backend, Web, infra, AWS, Terraform, Integration, and Java.