Vasanth Rajendran

Abstract: This talk explores how generative and multimodal AI systems are transforming product discovery, personalization, and decision making in modern retail environments. The session explains how search engines and product platforms combine embeddings, retrieval models, and multimodal understanding to interpret both images and text. The talk also covers how generative models create content across text, imagery, and layout structures; how quality, safety, and approval systems validate content before publication; and how these pipelines are deployed at scale in consumer-facing products. The session concludes with an outlook on next generation agent based automation, multimodal model capabilities, and emerging research directions. The content is designed to be accessible to students, engineers, and AI enthusiasts without requiring deep familiarity with low-level systems.

Biography:

Mr. Vasanth Rajendran holds a Master of Science in Computer Science from the University of Illinois Chicago and a Bachelor of Engineering in Computer Science from Anna University. Mr Rajendran has fourteen years of experience in artificial intelligence, large scale system design, and applied machine learning. Mr Rajendran currently leads engineering programs in generative content systems, multimodal search, personalized discovery, and automated content validation at Amazon supporting global retail customers. Vasanth’s research interests include generative models, multimodal understanding, deep reinforcement learning, and temporal pattern analysis. Vasanth has published several peer reviewed works in IEEE venues and serves as a reviewer and committee member for computing and AI conferences. Vasanth also volunteers as a judge and mentor for student innovation and engineering programs.

Address:Colorado, United States