FMOps/LLMOps for FMs with Amazon SageMaker and Amazon Bedrock

Creating reliable and repeatable workflows for generative AI applications requires additional tooling and practices that build on traditional MLOps.

In this session, get a comprehensive overview of lifecycle management for foundation models from Amazon SageMaker JumpStart and Amazon Bedrock that power your generative AI applications.

Dive deep into operational efficiencies across the lifecycle, including model selection and customization, model evaluation, model deployment, augmentation workflows, monitoring and traceability, and ongoing management. Explore multiple Amazon SageMaker MLOps services (such as SageMaker Experiments, SageMaker Pipelines, SageMaker Model Registry, and Model Monitor) for the reference architectures presented in this session.