Kareem Syed-Mohammed

Enterprises that own their AI lifecycle across training and inference can adapt their models as fast as their users' need change. Vanguard outgrew off the shelf models and built infrastructure that runs custom large language models (LLMs) and specialized small language models (SLMs) side by side.

AI agents are moving from research prototypes to real-world applications powering copilots, automation flows, and customer-facing assistants. But building agents that are reliable, observable, and scalable is still challenging.

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.

Teams across organizations are training new models, fine-tuning them with their data, and running inference at scale—all of which requires timely access to accelerated compute resources.

In this workshop, learn how you can bring data insights to your internal teams and end customers by simply and seamlessly embedding rich, interactive data visualizations and dashboards into your web applications and portals. You must bring your laptop to participate.