Powering the Future: Building Your GenAI Infrastructure Stack

Summary

Disclaimer: This summary has been generated by AI. It is experimental, and feedback is welcomed. Please reach out to info@qconsf.com with any comments or concerns.

The presentation titled Powering the Future: Building Your GenAI Infrastructure Stack by Merrin Kurian highlights the construction of a generative AI infrastructure within Intuit. Here is a structured summary of the key points:

Introduction

Merrin Kurian, a Distinguished Engineer at Intuit, discusses the integration of AI agents in product experiences and the development of Intuit's GenoS (Generative AI Operating System). The presentation aims to elaborate on the components necessary to build, buy or borrow for scaling AI solutions while maintaining governance and cost control.

  • Intuit's mission focuses on empowering prosperity globally through an AI-driven expert platform serving approximately 100 million users.
  • Intuit's platform achieves scale by generating 60 billion ML predictions daily and managing massive financial operations, including processing $2 trillion in invoices.

AI Agent Development and GenoS Platform

The platform, GenoS, accelerates AI-powered experiences through user experience elements and developer tools. It includes various components like GenUX, developer tooling, and agent starter kits to facilitate a seamless development process.

  • Prompt management and evaluation systems are provided for developers to manage their AI projects efficiently.
  • The system supports rapid experimentation and assessments to enhance agility and adaptability in AI development.

Challenges and Solutions

Kurian addresses challenges like prompt portability and the subjectivity of LLM applications compared to traditional applications. Emphasizing the need for robust infrastructure and redefined evaluation criteria, she highlights the importance of continuous improvement and adaptation.

Conclusion

The presentation concludes with lessons learned on AI governance, emphasizing collaboration with industry standards, and continuous platform evolution to meet both regulatory and technological demands.

Overall, the talk provides a comprehensive look at scaling AI applications within an enterprise while focusing on infrastructure, collaboration, and governance.

This is the end of the AI-generated content.


Abstract

Behind every productivity leap is a rock-solid platform. Go under the hood with Intuit’s GenOS team to see how vector stores, prompt management, RAG pipelines, and agent orchestration come together to serve ~100 million users. You’ll leave knowing which components to build, buy, or borrow—and how to scale from pilot to enterprise without sacrificing governance or cost control.

Interview:

What is your session about, and why is it important for senior software developers?

This session will provide an insight into the platform capabilities required for powering AI Agent development at scale.

Why is it critical for software leaders to focus on this topic right now, as we head into 2026?

As we understand how to leverage AI Agents into product experiences, this topic provides the right understanding of what goes behind developing reliable Agents at scale with outcomes achieved.

What are the common challenges developers and architects face in this area?

There are quite a few skills software engineers need to pick up to transition to effective AI engineers. There are also new challenges with designing systems that incorporate AI Agents into existing enterprise ecosystems. This session covers both.

What's one thing you hope attendees will implement immediately after your talk?

I hope that attendees will walk away with clear visibility into the challenges in developing reliable agents at scale and have an understanding of the capabilities that will enable them to overcome them.

What makes QCon stand out as a conference for senior software professionals?

QCon is a conference that brings together industry leaders to share insights into the latest technologies with a practitioner view. Builders greatly benefit from both learning what’s new and how it applies to them.


Speaker

Merrin Kurian

Distinguished Engineer @Intuit

Merrin Kurian is a Distinguished Engineer at Intuit, leading AI Foundation capabilities powering Classic AI, Generative AI and Agentic AI experiences in Intuit's portfolio of products. Her current role plays neatly into her two areas of interest: AI and Platform engineering. She has previously led Platform Engineering for QuickBooks and has driven several technology transformations including Public Cloud adoption and Event driven Microservices at Intuit. She has over 17 years of experience in the industry and has dual degrees in Computer Science & Business Administration from BITS, Pilani, India.

Read more
Find Merrin Kurian at:

Date

Wednesday Nov 19 / 01:35PM PST ( 50 minutes )

Location

Ballroom BC

Topics

AI/ML Agents GenAI Core AI Platform RAG Agentic AI Developer Productivity

Slides

Slides are not available

Share

From the same track

Session AI/ML

Accelerating LLM-Driven Developer Productivity at Zoox

Wednesday Nov 19 / 11:45AM PST

Over the past year, Zoox has invested in integrating Large Language Models (LLMs) into the entire developer lifecycle through a companywide initiative called Zoox Intelligence (ZI).

Speaker image - Amit Navindgi

Amit Navindgi

Staff Software Engineer, Developer Experience @ Zoox, Leading Applied AI Initiatives

Session AI/ML

AI-Driven Productivity: From Idea to Impact

Wednesday Nov 19 / 02:45PM PST

In this session you'll learn how product leaders turn GenAI enthusiasm into an enterprise-ready blueprint for real productivity gains.

Speaker image - Jyothi Nookula

Jyothi Nookula

Product Leader Director with 13+ Years Driving AI Product & Platform Innovation, Previously @Meta, @Amazon, and @Etsy

Session AI/ML

Choosing Your AI Copilot: Maximizing Developer Productivity

Wednesday Nov 19 / 10:35AM PST

The AI coding agent landscape evolves weekly. This talk compares today’s frontrunners, shows where each shines, and shares prompts, policies, and “rules templates” that turn code suggestions into production-quality output.

Speaker image - Sepehr Khosravi

Sepehr Khosravi

Machine Learning Platform Engineer @Coinbase, Award Winning Instructor @UC Berkeley - Gen-AI Bootcamp, Founder @ AI Scouts

Session AI/ML

Trustworthy Productivity: Securing AI-Accelerated Development

Wednesday Nov 19 / 03:55PM PST

Autonomous agents operate in a continuous loop: perceive context → reason → execute tools → observe. Each edge creates distinct attack surfaces. This talk maps vulnerabilities—memory poisoning in context ingestion, goal hijacking during reasoning, blind execution at the action stage.

Speaker image - Sriram  Madapusi Vasudevan

Sriram Madapusi Vasudevan

Senior Software Engineer @AWS Agentic AI, Previously Core Team @AWS SAM, AWS Cloudwatch, Core Developer @Openstack