Summary
Rohun Tripathi is a research engineer specializing in computer vision and multimodal machine learning with 11 years of experience, currently advancing generative AI research at the Allen Institute for AI after a multi-year tenure at Amazon. At Amazon he applied diffusion models, GANs, NeRFs and transformer-based multimodal embeddings to problems ranging from automated ad/image generation to deployed perception systems in cashierless stores and Prime Video, with publications in venues like ICASSP. He holds an MS from Cornell Tech and a CS degree from IIT Kanpur, and his background bridges both research and production: moving models from papers into real-world services and retail deployments. Based in Seattle, he brings a strong applied-research mindset and cross-domain experience spanning video action recognition, audio-video synchronization, and privacy-aware IoT sensing. Notably, his work has contributed to visible consumer products (Amazon Ads image generator, Just Walk Out stores) while continuing to push foundational multimodal modeling.
11 years of coding experience
8 years of employment as a software developer
Indian Institute of Technology Kanpur
Masters Computer Science, Masters Computer Science at Cornell Tech
English, Hindi