The international software development conference for senior software developers, architects, and technical leaders focuses on proven patterns from engineering leaders who are building and scaling real-world AI systems.
QCon San Francisco Software Development Conference Nov 17-21, 2025.
SAN FRANCISCO, Oct. 26, 2025 /PRNewswire-PRWeb/ -- QCon San Francisco, the international software development conference for senior software engineers, architects, and technical leaders, returns to the Hyatt Regency from November 17-21, 2025. The program is curated by senior software practitioners to provide proven, practitioner-led patterns, not hidden product pitches, to help technical leaders shape the next 3-5 years of software development.
As senior technologists are tasked with moving AI from experimentation to enterprise-scale production, they face a critical challenge: cutting through the hype to find what actually works. QCon San Francisco's 2025 AI program is curated to solve this challenge by focusing on the "how-to" of building, scaling, and operating reliable, AI-driven systems.
"Senior engineers don't need another talk on 'what is GenAI," said Hien Luu, QCon San Francisco 2025 Program Committee member. "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 the peers who have already solved them."
The QCon San Francisco program features AI-related sessions across its 15 technical tracks, highlighting real-world lessons.
Highlights from the AI engineering-focused sessions include:
- Engineering at AI speed: Learn the architectural decisions for prioritizing speed over complexity in agentic systems, from Adam Wolff, who leads engineering at Anthropic.
- Building a GenAI infrastructure stack: See how vector stores, RAG pipelines, and agent orchestration serve ~100 million users, from Maggie Hu and Merrin Kurian at Intuit.
- Agentic AI for enterprise data: Get a case study on transforming complex enterprise data into actionable intelligence, from Vinaya Polamreddi of Glean.
- Accelerating LLM-driven productivity: Get a practical blueprint and organizational strategies for scaling an organization's AI capabilities, from Amit Navindgi at Zoox.
- Personalization with LLMs: A deep dive into redefining personalization by tightly integrating LLMs, from Sudeep Das and Pradeep Muthukrishnan at DoorDash.
- Autoscaling multi-model LLM serving: A technical breakdown of autoscaling multi-model serving with shared weights and hot-swapped adapters, from Meryem Arik of Doubleword.
- Designing fast LLM UX in mobile: Get insights on designing fast, reliable, and engaging LLM-powered mobile app experiences, from Bala Ramdoss at Amazon.
These sessions are designed to help software development teams validate their own roadmaps, de-risk complex technical decisions, and accelerate their team's adoption of AI.
For a detailed look at all AI engineering sessions, speaker bios, and the full conference schedule, visit the official QCon San Francisco AI engineering topic page: https://qconsf.com/ai-engineering
Media Contact
QCon Team, QCon San Francisco, 44 020 7558 8102, [email protected], https://qconsf.com/
SOURCE QCon San Francisco
Share this article