Search AWS Educational Content

While running inference in the cloud is a common and effective approach for Generative AI, some use cases demand local execution. This session explores how to design and operate local inference architectures using AWS IoT Greengrass. Through a live demo using a robotic arm, attendees compare cloud-based and local inference in practice, examining trade-offs in latency, connectivity, and model update frequency.

Learn how to optimize and deploy popular open-source models like Qwen3, GPT-OSS, and Llama4 using advanced inference engines such as vLLM on SageMaker. We'll explore key features including bidirectional streaming for audio and text applications, and share proven optimization techniques for inferencing. Through live demos, learn to boost performance with KV caching, intelligent routing, and autoscaling to maintain stability under varying loads.

Strava built its Athlete Intelligence feature using Claude by Anthropic in Amazon Bedrock, providing tailored insights safely in a friendly brand voice to help athletes interpret their activity data. Using Amazon Bedrock Guardrails, Strava is able to detect factual errors, filter harmful content, and mitigate undesirable topics—helping Athlete Intelligence deliver positive and encouraging insights. Case Study: https://go.aws/4qOXlK3 Subscribe to AWS: https://go.

Dive deep into strategies for planning your large-scale AWS migration. In this session, we'll explore how to use AWS Transform and AI agents to accelerate your discovery, assessment, and planning for large-scale migrations. We will show you how planning migrations in spreadsheets is a thing of the past and how AI agents remove the heavy manual work of curating discovery data, building a business case, and planning a migration. Learn more: More AWS events: https://go.

Want to learn how Amazon S3, one of the world's largest distributed systems, manages software deployments at scale? This session reveals practical insights into our deployment tools, feature flag strategies, and progressive rollout techniques that enable reliable updates at massive scale. We'll share real-world lessons learned from critical deployments, including how we handle rollbacks, manage dependencies, and monitor service health during updates.

Murali Brahmadesam, Razorpay CTO giving on how AWS Enterprise Support helped Razorpay in achieving Organizational governance. Subscribe to AWS: https://go.aws/subscribe Sign up for AWS: https://go.aws/signup AWS free tier: https://go.aws/free Explore more: https://go.aws/more Contact AWS: https://go.aws/contact Next steps: Explore on AWS in Analyst Research: https://go.aws/reports Discover, deploy, and manage software that runs on AWS: https://go.

Learn how to fine-tune a foundation model using fully managed training jobs or Amazon SageMaker HyperPod on custom dataset. Subscribe to AWS: https://go.aws/subscribe Create a free AWS account: https://go.aws/signup Try AWS for free: https://go.aws/free Connect with an expert: https://go.aws/contact Explore more: https://go.aws/more Next steps: Explore on AWS in Analyst Research: https://go.aws/reports Discover, deploy, and manage software that runs on AWS: https://go.

Build with fully managed integrated development environment (IDE) for R with a console, a syntax-highlighting editor that supports direct code execution, and tools for plotting, history, debugging, and workspace management. Use preconfigured R packages such as devtools, tidyverse, shiny, and rmarkdown to generate insights, and publish them using RStudio Connect. Seamlessly switch within RStudio, JupyterLab, and Code Editor IDEs for R and Python development.

Everyone talks about data governance — but few can explain what it actually means in practice. In this episode, we break it down to its essentials: understanding, curating, and protecting data so it supports real business outcomes. You’ll learn why data governance isn’t about control or bureaucracy, but about enabling trust, quality, and business value. We’ll also share how to get started and what not to measure when building your program. Learn more about Amazon SageMaker Catalog - http://go.

Discover an innovative approach to load balancing where targets actively control load distribution. Traditional load balancers use a push model with predefined algorithms, but this new paradigm implements a pull model that empowers targets to manage their own load. Join us to explore how this new mechanism delivers superior application performance and high target efficiency. Learn more: More AWS events: https://go.aws/3kss9CP Subscribe: More AWS videos: http://bit.

AstraZeneca is on a mission to deliver 20 life-changing medicines by 2030, and is leveraging agentic AI technology to make it happen. The company has implemented AI solutions throughout their organization, revolutionizing their data management and analysis capabilities. Through their innovative approach of using modular, multi-agent AI systems, AstraZeneca has deployed multiple AI tools into production across multiple business units.

Catch up on the most important insights, ideas, and product reveals from the What's Next with AWS livestream event. Find out what's next in agentic AI with AWS and OpenAI leaders, including Matt Garman, Sam Altman, Colleen Aubrey, and Julia White. Subscribe to AWS: https://go.aws/subscribe Create a free AWS account: https://go.aws/signup Try AWS for free: https://go.aws/free Connect with an expert: https://go.aws/contact Explore more: https://go.