Nagaraj Sengodan
Solution Architect, Capgemini
Watford, United Kingdom
Actions
Nagaraj Sengodan, an experienced cloud data professional who specializes in Consulting, Data Strategy, Solution Architecture, and Solution Implementation of Data Management initiatives. With a wealth of expertise, he has a proven track record of engineering large-scale data platforms that enable enterprises to become data-driven institutes and excels in guiding organizations towards leveraging their data assets effectively
Area of Expertise
Topics
Azure AI Foundry : Generative AI Development Hub
Azure AI Foundry provides user-friendly platforms that simplify the process of building Generative Artificial Intelligence (AI) applications. This session will guide you through building generative AI solutions using language models and prompt flow, enabling your applications to deliver meaningful value to users. Explore the Azure AI Foundry model catalog, which features a variety of open-source models, and learn how to select, deploy, and fine-tune a model to meet your specific needs.
Finally, explore how to evaluate and optimize your generative AI applications using Azure AI Studio. Learn techniques to test performance, refine user experiences, and ensure your applications deliver accurate responses consistently.
LLMOps: Operationalizing Large Language Models for the Real World
Large Language Models (LLMs) like OpenAI GPT,/Groovy Google Gemini, and Databricks DBRX are transforming industries, but effectively deploying and managing them requires more than traditional machine learning practices. LLMOps is a specialized set of techniques, tools, and workflows designed to tackle the unique challenges of working with LLMs in production. This presentation will explore what makes LLMOps distinct, why its essential, and how it enables organizations to harness the power of LLMs efficiently, at scale, and with reduced risks.
Introduction to LLMOps: Overview of its components from data preparation to deployment and monitoring
MLOps to LLMOps: Key differences including computational demands, fine-tuning with human feedback, and prompt engineering
Challenges & Solutions: Addressing LLM-specific issues like inference cost, model drift, and hallucination
Best Practices: Insights into data prep, governance, CI/CD pipelines, and model monitoring
Platform Tools: Exploring platforms like MLflow and Databricks for effective LLMOps implementation
Retrieval Augmented Generation (RAG) with Azure AI Search
In this presentation, we will explore the concept of Retrieval Augmented Generation (RAG) and how it can leveraged particularly in the context of enterprise solutions. RAG architecture provides the ability to create generative AI to your own proprietary content, which ensure that the information used to generate responses is tailored to specific business needs.
The key to a successful RAG architecture is the information retrieval system, which determines the inputs to the LLM. We will discuss the critical requirements for this system, including scalable indexing strategies, relevant query capabilities, security, global reach, and seamless integration with embedding and chat/language models. Azure AI Search emerges as the ideal solution. Microsoft offers several built-in approaches for using Azure AI Search in a RAG solution, such as Azure AI Studio, Azure OpenAI Studio, and Azure Machine Learning. We will also explore a custom RAG pattern that gives you more control over the architecture. This pattern outlines a step-by-step process of sending the user's prompt to Azure AI Search, retrieving the most relevant information, and then passing it to the LLM to generate the final response.
By the end of this presentation, you will have a comprehensive understanding of how to leverage Azure AI Search within a RAG architecture, empowering you to build enterprise-grade generative AI solutions that harness the power of your own proprietary content.
Practical Data Engineering: Build Reliable and Cost Effective Data Pipelines
Get ready for a hands-on journey in our session, We'll show you how to create data pipelines that are not only reliable but also cost-effective, and enhanced autoscaling. From learning the basics of enhanced autoscaling to applying it in real world situations, this session is all about helping you become a pro at building data pipelines.
Discover the secrets of enhanced autoscaling and find out how to balance reliability and cost efficiency. Join us for this practical exploration where we simplify the world of data engineering, giving you practical skills to boost your pipeline-building abilities.
Key Highlights:
Introduction to the Data Intelligence Platform
Change Data Capture with SCD1 and 2
Mastering Databricks Workflows with advanced control flow and triggers
Generative AI for Data Engineers
Understand data governance and lineage with Unity Catalog
Benefits of Serverless Compute
Delta Live Tables: Building reliable data pipelines
In this engaging session, we explore the
Delta Live Tables and its huge impact on current data analytics platforms.
Delta Live Tables from Azure Databricks simplifies the process of creating robust and maintainable data processing pipelines. With this declarative framework, its easier to manage complex data transformation, monitoring, data quality, and error handling.
Real Time Analytics In Microsoft Fabric
In today's data-driven world, businesses need to analyze data in real-time and generate value out of it using machine learning. However, ensuring the timely development and deployment of these technologies is crucial to harness their potential effectively. In this talk, I will delve into Microsoft Fabric – Saasified Data Platform, and share our approach to implementing them to ensure we’re achieving business goal.
During the session, We'll explore practical demonstrations that showcase the real-time analytics and machine learning features, demonstrating how they provide a business value much faster in today's fast-paced market
Join us in this session to explore the dynamic synergy of real-time analytics and machine learning, enhancing your business's agility
Ask the Expert - Group B (Fri - 10:10 to 11:00)
'Got a problem? Don't know who to call? Bring it to SQLBits and get it solved by our panel of experts!
More information can be found here:
https://sqlbits.com/news/ask-the-experts-at-the-experts-lounge/
5. Data Science and Analytics: Paul Andrew, Nagaraj Sengodan
7. Programming and Development:, Niall Langley, Sander Stad
8. Data Management and Governance:Nagaraj Sengodan
9. User Experience and Design: Ashley Graham Brown
Ask the Expert - Group A (Wed 11:10 to 13:00)
'Got a problem? Don't know who to call? Bring it to SQLBits and get it solved by our panel of experts!
More information can be found here:
https://sqlbits.com/news/ask-the-experts-at-the-experts-lounge/
1. SQL and Databases:
2. Microsoft Fabric and Related Technologies:
3. Power BI and Data Visualization:
4. Azure and Cloud Technologies:
11:10 to 12:00
1. Magi Naumova
2. Paul Andrew, Brynn Borton
3. James Dales
4.
12:10 to 13:00
1. Martin Catherall & Heid Hasting
2. Freddie Santos, Nagaraj Sengodan
3. Kristoffer West, Mark Hayes
4.
Ask the Expert - Group A (Fri, 13:40 to 14:30)
Got a problem? Don't know who to call? Bring it to SQLBits and get it solved by our panel of experts!
More information can be found here:
https://sqlbits.com/news/ask-the-experts-at-the-experts-lounge/
1. SQL and Databases: Andrew Pruski
2. Microsoft Fabric and Related Technologies: Johan Ludvig Brattas, Reitse Eskens
3. Power BI and Data Visualization: Gregor Brunner, Marjolein Opsteegh
4. Azure and Cloud Technologies: Nagaraj Sengodan, Rune Ovlien Rakeie
Data Quality Revolution : The Fabric-OpenAI Approach
In this session, we'll walk you through practical techniques for handling various data issues, such as formatting problems, conversion, and more. Whether you're a seasoned data professional or just starting your data journey, this session will equip you with the skills and knowledge needed to turn chaotic datasets into valuable insights. Don't miss this opportunity to master the art of data cleaning with Fabric and Open AI.
Real-time Analytics & Machine Learning Models with Microsoft Fabric
In today's data-driven world, businesses need to analyze data in real-time and generate value out of it using machine learning. However, ensuring the timely development and deployment of these technologies is crucial to harness their potential effectively. In this talk, I will delve into Microsoft Fabric – Saasified Data Platfrom, and share our approach to implementing them to ensure we’re achieving business goal.
During the session, We'll explore practical demonstrations that showcase the real-time analytics and machine learning features, demonstrating how they provide a business value much faster in today's fast-paced market
Join us in this session to explore the dynamic synergy of real-time analytics and machine learning, enhancing your business's agility
Empowering Enterprises with Microsoft Fabric:The Ultimate Analytics Solution for Onelake & Lakehouse
Join us in this enlightening session as we explore the transformative capabilities of Microsoft Fabric, all-in-one analytics solution designed to seamlessly integrate OneLake and lakehouse architectures within enterprises
OneLake, the foundational element of Microsoft Fabric, simplifies the storage and access, organizational data which is built on Azure Data Lake Storage (ADLS) Gen2, OneLake. It empowers both professional and citizen developers by providing a centralized, tenant-wide data store, enabling effortless data discovery, sharing, and compliance enforcement
During our session, we will delve into the key components of Microsoft Fabric and showcase how it revolutionizes data storage and management. We will discuss the concept of Lakehouses and highlight their importance in bringing together data processing and analytics to gain valuable insights that Microsoft Fabric opens up
Data Relay 2024 Sessionize Event
SQLBits 2024 - General Sessions Sessionize Event
Data Relay 2023 Sessionize Event
Microsoft Data Platform Group - Birmingham User group Sessionize Event
Please note that Sessionize is not responsible for the accuracy or validity of the data provided by speakers. If you suspect this profile to be fake or spam, please let us know.
Jump to top