Simon Zamarin

Looking to build powerful AI agents that scale with enterprise-grade reliability? In this hands-on workshop, you’ll use the Strands SDK to develop agents quickly, then deploy them using Amazon Bedrock AgentCore’s secure, serverless runtime with built-in session isolation.

In this chalk talk, discover how to host foundation models to build generative AI applications at scale and dive deep into the challenges of hosting large models that span across GPUs. Explore various model optimization techniques such as quantization, compilation, tensor parallelism, and continuous batching.

Scaling deep learning programs into production often comes with its challenges, and you can’t have high quality data modeling if your storage isn’t optimized for performance scalability. Getting this wrong can lead to unexpected cost and performance issues.

Jupyter notebooks allow data scientists to create, share, and streamline work for data visualization from raw code to fully functional machine learning (ML) models. With Amazon SageMaker Studio, you can spin up Jupyter notebooks quickly without the need to manage the underlying compute resources.