Modern Data Engineering for AI Applications with Microsoft Fabric

AI applications are only as strong as the data platforms behind them.
Learn from industry experts as they share practical approaches to building scalable, production-ready AI systems, covering modern data engineering, Retrieval-Augmented Generation (RAG), and multilingual AI.

## 🎤 Session 1

The Self-Correcting RAG: Improving Retrieval via User Feedback Loops

Nutan Sahoo
Applied Scientist, Microsoft

Your RAG pipeline was built to surface the right answers, so why does it keep retrieving the wrong documents?
Standard Retrieval-Augmented Generation works well out of the box, but in specialized technical domains, general-purpose embeddings struggle with internal terminology, jargon, and nuanced context. The conventional fix, fine-tuning models or rebuilding embeddings, is expensive, slow, and breaks down the moment your knowledge base changes.
There's a better way. In this workshop, we'll introduce FLAIR (Feedback Learning for Adaptive Information Retrieval), a lightweight framework that continuously adapts your retrieval strategy using domain-expert feedback, no model re-training required. You'll learn how FLAIR:
- Gathers real and LLM-synthesized query indicators offline to understand what experts actually need
- Deploys a two-track online ranking system that dynamically promotes relevant documents and filters out past retrieval errors, in real time
- Evolves with your knowledge base so retrieval quality improves continuously with expert feedback
Who is this for? Anyone interested in RAG, and those building or maintaining RAG systems.
📄 Link to the paper for reference-FLAIR: Feedback Learning for Adaptive Information Retrieval

***

## 🎤 Session 2

AI Beyond English: Building Multi-Lingual AI Solutions

Rachel Wagner-Kaiser, Ph.D.
Director, Data Scientist, KPMG

This talk addresses the core challenges technical teams face when dealing with non-English languages in building effective AI solutions, reinforced by real-life examples. We will outline the complexity of non-English data, from tackling non-Latin character sets and low-resource languages to the practical hurdles of transforming unstructured data (like images and audio) into usable text. We will also go into the options for different technical approaches, including topics such as the complexity of language detection and cross-language processing techniques. The session will also analyze the current role and limitations of LLMs across diverse languages. We will conclude with best practices for designing and deploying high-performance, multilingual NLP systems that deliver value for practical business use cases.Who Should Attend?

• Software Engineers
• Data Engineers
• AI/ML Engineers
• Data Scientists
• Architects
• Anyone interested in building production-ready AI systems

Come connect with the PyData Seattle community, learn from experienced industry practitioners, and discover how modern data engineering powers the next generation of AI applications.

📅 Date: Tuesday, August 25, 2026
🕠 Time: 5:30 PM – 6:30 PM PT
📍 Format: Virtual (Microsoft Reactor Livestream)