Isha Dua

Learn how to build efficient generative AI solutions using AWS services like SageMaker and Bedrock. We'll explore practical optimization techniques including quantization and pruning, along with cost-saving infrastructure features such as spot instances and intelligent storage tiering.

Building sustainable, cost-effective generative AI on AWS requires integrating agentic AI, efficient architecture, and cloud-native optimization. Agentic systems using Amazon Bedrock AgentCore employ contextual memory, asynchronous execution, and on-demand tool invocation to minimize compute waste.

With the increasing complexity, scale, and adoption of AI workloads, it is important to consider their environmental impact. This chalk talk provides environmental sustainability insights that are specific to large language models and how machine learning operations (MLOps) is critical to sustainable optimization.

With the increasing complexity, scale, and adoption of AI workloads, it is important to consider their environmental impact. This lightning talk provides environmental sustainability insights that are specific to large language models and how machine learning operations (MLOps) is critical to sustainable optimization.

Since 1990, the earth has lost about one billion acres of forest, according to the Food and Agriculture Organization of the United Nations. In this workshop, learn how to track deforestation caused by fires and forest cutting using Sentinel-2 satellite imagery and visualize changes using Amazon SageMaker Studio labs.