Demystify Fine-Tuning A Language model Using KAITO on Azure Kubernetes Service

Learn the fine-tuning process of large language models using KAITO on Azure Kubernetes Service (AKS) in this hands-on technical session. We will walk through what is the Kubernetes AI Toolchain Operator (AI), review the fine-tuning data set, phi-3 pretrained model, fine-tuning workspace Kubernetes job, review fine-tuned model stored in azure container registry and finally deploy the fine-tuned model and evaluate with prompts from the fine-tuned dataset. You will gain the fundamental concepts to fine-tune with your own datasets and pre-trained models.

Overview of RAG Chat App Using Azure AI Foundry SDK and AI Search

Join me for an engaging deep-dive session where you'll discover how to build an intelligent chat application using Azure's cutting-edge AI services of Azure AI Foundry SDK and Azure AI Search. I will walk through architecture, code flow, data flow, prompt templates and Azure AI services configuration. By the end of this session, you'll have the knowledge and code samples needed to build your own AI-powered chat applications.

Deploying AI RAG on AKS with KAITO: Architecture, Ingestion, and Streamlit Chatbot

In this session, we’ll go end-to-end and build a real RAG system on Azure Kubernetes Service (AKS) using the KAITO RAG Engine.

You’ll see how to:
- Install and run KAITO RAG Engine on AKS
- Understand the RAG architecture (ingestion, embedding, retrieval, inference)
- Ingest and index real documents into the RAG Engine
- Connect the system to a Streamlit-based chatbot UI
- Query your own data using an LLM—live and in real time

The session is practical, code-driven, and demo-heavy, with a focus on how these components fit together in a cloud-native, scalable architecture.

Whether you’re a cloud engineer, platform engineer, or AI developer, you’ll walk away with a clear mental model—and a working reference—of how to deploy RAG systems on Kubernetes.

Prefer time slot in between 10am to 2pm. Otherwise, flexibile.

A Multi-Model Personal Health Agent with MS AI Foundry, KAITO, and Azure Kubernetes

This session reviews a Personal Health Agent hosted in AKS that supports both Microsoft AI Foundry hosted LLMs and AKS KAITO hosted LLMs.
A demo will cover scenarios of storing health profiles and photos of meals and infer macronutrients and store in an Azure SQL DB for long-term agent memory. Then ask questions to the agent about past health history, historical calorie deficits, health goal tracking for weight loss, and much more.
It covers the application architecture, Microsoft Agent Framework orchestration, Streamlit front end, durable memory design, and model selection across cloud and AKS in-cluster backends with KAITO LLM hosted models such as phi 3.5 vision.