Discover how to deploy NVIDIA Llama Nemotron models on AWS Bedrock Marketplace in this 10-minute conference talk from the AWS OnAir NY Summit 2025. Learn why Nemotron models, which are part of NVIDIA NIM inference microservices, are essential for building agentic AI solutions and how they integrate seamlessly with AWS managed services including Amazon EC2, Amazon EKS, and Amazon SageMaker AI to enable large-scale generative AI model deployment. Explore the capabilities of the NVIDIA GB200 NVL72 platform with NVIDIA NVLink, now available as Amazon EC2 P6-GB200 instances, which provides the computational power needed for training and inference at scale to drive breakthrough innovations across drug discovery, enterprise search, software development, and other critical applications. Gain practical insights into leveraging these cutting-edge technologies to build and deploy sophisticated AI agents that can transform your organization's AI capabilities.