QCon San Francisco 2025: Senior Engineers Share Production Blueprints for De-Risking Agentic AI and GenAI Infrastructure
**QCon San Francisco 2025: The Premier Software Development Conference for Senior Engineers and AI Leaders**
*November 17-21, 2025 | Hyatt Regency, San Francisco*
QCon San Francisco, the international software development conference tailored for senior software developers, architects, and technical leaders, is returning to the Hyatt Regency from November 17-21, 2025. Known for its practitioner-led approach, QCon focuses on delivering proven patterns and insights directly from engineering leaders — not product pitches — to empower technical leaders in shaping the future of software development over the next three to five years.
As the industry rapidly evolves, senior technologists face a critical challenge: moving AI from experimental projects to enterprise-scale, production-grade systems. Cutting through the hype to find practical, reliable solutions is essential. QCon San Francisco’s 2025 AI program is meticulously curated to address this challenge by delivering actionable knowledge on building, scaling, and operating dependable AI-driven systems.
> “Senior engineers don’t need another talk on ‘what is GenAI,’” said Hien Luu, member of the QCon San Francisco 2025 Program Committee. “They need to know how to de-risk its adoption. They’re asking: ‘How do I build a production-grade infrastructure for this? How do I validate my architecture for an agentic system?’ Our AI sessions are built to answer those specific questions, directly from peers who have already solved them.”
### Highlights from QCon San Francisco 2025 AI Engineering Sessions
The conference features AI-related content across 15 technical tracks, focusing on real-world use cases and lessons learned. Some of the standout sessions include:
– **Engineering at AI Speed**
Explore architectural decisions that prioritize speed over complexity in agentic systems, presented by Adam Wolff, Head of Engineering at Anthropic.
– **Building a GenAI Infrastructure Stack**
Discover how vector stores, Retrieval-Augmented Generation (RAG) pipelines, and agent orchestration serve approximately 100 million users, presented by Maggie Hu and Merrin Kurian from Intuit.
– **Agentic AI for Enterprise Data**
Get an in-depth case study on transforming complex enterprise data into actionable intelligence from Vinaya Polamreddi of Glean.
– **Accelerating LLM-Driven Productivity**
Learn practical blueprints and organizational strategies for scaling AI capabilities within an organization, shared by Amit Navindgi of Zoox.
– **Personalization with Large Language Models (LLMs)**
Dive deep into redefining personalization through tight integration of LLMs, presented by Sudeep Das and Pradeep Muthukrishnan from DoorDash.
– **Autoscaling Multi-Model LLM Serving**
Gain technical insights into autoscaling multi-model serving with shared weights and hot-swapped adapters, delivered by Meryem Arik of Doubleword.
– **Designing Fast LLM UX in Mobile**
Explore strategies for designing fast, reliable, and engaging LLM-powered mobile app experiences with Bala Ramdoss from Amazon.
These sessions are crafted to help software development teams validate their roadmaps, de-risk complex AI adoption decisions, and accelerate the integration of AI technologies within their organizations.
For a comprehensive look at all AI engineering sessions, speaker biographies, and the full conference schedule, please visit the official [QCon San Francisco AI Engineering topic page](#).
—
**Media Contact:**
QCon Team, QCon San Francisco
Phone: +44 020 7558 8102
Email: [email protected]
*Source: QCon San Francisco*
https://www.prweb.com/releases/qcon-san-francisco-2025-senior-engineers-share-production-blueprints-for-de-risking-agentic-ai-and-genai-infrastructure-302593972.html
You may also like
Leave a Reply