Coursera Flash Sale
40% Off Coursera Plus for 3 Months!
Grab it
Learn to customize foundation models and deploy AI agents at scale using Amazon SageMaker AI in this comprehensive conference talk from AWS re:Invent 2025. Explore the complete end-to-end journey of building performant agentic workflows with customized open-weight models, starting with model customization using Amazon SageMaker AI and experiment tracking through managed MLflow. Discover how to establish proper governance with Amazon SageMaker AI Model Registry and deploy optimized models using SGLang on Amazon SageMaker AI Inference for low-latency agent applications. Master the creation of repeatable, auditable workflows with Amazon SageMaker AI Pipelines while maintaining comprehensive observability and control for production AI systems. Watch a live demonstration of customizing and deploying an open-weight model, and gain valuable insights from SGLang's team on inference optimization for AI agents.
