Suman Debnath

While many developers can download a model from Hugging Face, few grasp why latency spikes the moment concurrent users hit an endpoint. This talk explores the "physics" of LLM inference, emphasizing that engineering a production-grade service requires understanding hardware constraints rather than just adding more GPUs.

Building AI agents used to require complex orchestration, extensive scaffolding, and months of tuning. With Strands Agents, an open source SDK from AWS. You can now build, test, and deploy intelligent agents in just a few lines of code.

Discover the transformative potential of Multimodal Agentic Retrieval-Augmented Generation (RAG) in this hands-on workshop. Participants will explore the integration of advanced AI engineering techniques with Amazon Nova to build systems that leverage text and image embeddings, LangChain, and Amazon Bedrock for creating context-aware multimodal AI agents.

Insurance companies manage extensive procedure documents, making manual processing time-consuming and complex. This session introduces a generative AI-based solution to automate and scale these operations.

Join this in-depth, technical chalk talk to explore the capabilities of Claude 3.5, the latest advancement in AI from Anthropic, and how to use it on AWS using Amazon Bedrock. This talk covers the advanced reasoning capabilities, prompt engineering techniques, and empirical evaluations of Claude 3.5.

As AI continues to transform industries, the applications of generative AI and LLMs are becoming increasingly significant. This session delves into the utility of these models across a variety of sectors, from fashion to entertainment and from cheminformatics to bioinformatics.

In this workshop we will walk through Polars step by step. Polars the fast-growing open source dataframe library that is becoming the go-to dataframe library for data scientists in python.

With the increase in popularity of online shopping, building an analytics platform for ecommerce is important for any organization, as it provides insights about the business, trends, and customer behavior. But, more importantly, it can uncover hidden insights that can trigger revenue-generating business decisions and actions.

In this session, learn how to build a machine learning (ML) model to classify music genres using a dataset of songs. See how to deploy this model to a serverless inference and then make it an API endpoint.

Recent advances in deep learning and natural language processing now make it possible for computers to write code and find bugs on their own. In this chalk talk, learn about transformer models and how to train one to generate code from a plain text input such as “write a program to read a file.” In the process, consider best practices for end-to-end machine learning workflows with Amazon...