Sandipan Banerjee is an applied scientist with 11 years of experience building multi-modal machine learning systems, currently designing multi-modal models for ads localization at Amazon. He holds a PhD in Computer Science from the University of Notre Dame and has driven research-to-product work across industry labs including Pipio, Samsung Research America, and Affectiva, with a strong focus on realistic avatar/video synthesis, GAN-based image-to-image rendering, and robust facial analysis. Sandipan’s portfolio blends foundational research—documented in a substantive publication record—with production engineering: pipelines for audio/image/embedding-driven avatar generation, lipsync and motion priors, and lightweight GAN frameworks for fast rendering. Notably, he has engineered perception-driven GAN losses and weakly supervised models that generalize across camera setups, a skillset that bridges academic rigor and deployed systems. Based in New York, he combines deep technical authorship with hands-on implementation, often turning synthetic-data insights into measurable improvements in recognition and behavior synthesis.
11 years of coding experience
12 years of employment as a software developer
Bachelor of Technology (B.Tech.) Computer Science, Bachelor of Technology (B.Tech.) Computer Science at National Institute of Technology Durgapur
Doctor of Philosophy (PhD) Computer Science, Doctor of Philosophy (PhD) Computer Science at University of Notre Dame
Find and Hire Top DevelopersWe’ve analyzed the programming source code of over 60 million software developers on GitHub and scored them by 50,000 skills. Sign-up on Prog,AI to search for software developers.