QCon Previews 20th Anniversary Conferences: Production AI, Resilience, and Staff+ Engineering

2026-02-10 · Source: InfoQ · Field: Technology & Digital — Artificial Intelligence & Machine Learning, Software Development & Engineering · Depth: Advanced, quick

Summary

QCon is celebrating its 20th anniversary with its 2026 conferences, QCon London (March 16–19) and QCon San Francisco (November 16–20), focusing on practical, production-ready insights from senior engineers. Key themes include the transition of AI from experimental LLMs to reliable "agentic systems," addressing non-determinism, observability, and security in production AI. The conferences will also emphasize "survivability" in complex distributed systems, advocating for cellular isolation and fault containment to limit failure "blast radius" rather than preventing all failures. Additionally, tracks will cover the human element of Staff+ Engineering, focusing on durable skills like technical judgment, and evaluating Platform Engineering ROI based on measurable outcomes like developer throughput and operational costs. Both events feature numerous peer-selected speakers.

Key takeaway

For AI Engineers moving models into production, you should prioritize understanding and mitigating non-determinism, observability, and security challenges in agentic systems. Focus on rigorous testing and validation to ensure probabilistic models perform reliably in live traffic, rather than solely on initial experimental success. Consider attending QCon London or San Francisco to gain practical insights on these specific production hurdles.

Key insights

QCon's 20th anniversary conferences focus on practical production challenges in AI, system resilience, and senior engineering roles.

Principles

• Prioritize survivability over simple uptime.
• Limit failure "blast radius" through fault containment.
• Evaluate platforms by measurable outcomes, not just adoption.

Method

The QCon approach involves curating sessions by senior engineers that focus on real-world successes and failures in production, moving beyond hype to discuss rigorous testing and validation for probabilistic models.

In practice

• Integrate models, tools, and workflows for agentic AI systems.
• Implement cellular isolation for distributed system resilience.
• Measure platform ROI via developer throughput and operational costs.

Topics

• Production AI
• Agentic Systems
• Distributed System Resilience
• Staff+ Engineering
• Platform Engineering ROI

Best for: Software Engineer, AI Engineer, MLOps Engineer

Related on AIssential

• Six Sessions at QCon AI Boston 2026 That Take Productionizing AI Seriously — The core challenge in productionizing AI agents lies in robust system engineering beyond model capabilities.
• QCon AI Boston 2026 Schedule: Agents in Production, Inference Cost, and AI in the SDLC — QCon AI Boston 2026 addresses the practical engineering challenges of deploying AI agents and models into production.
• not much happened today — Compact, multimodal AI models with extended context are enabling advanced on-device and agentic deployments, shifting focus to reliability and efficient operations.
• The Next Frontier of AI in Production Is Chaos Engineering — Chaos engineering needs an intent layer to ensure experiments are informative, not just safe.
• Why AI that works in the lab often fails in production — and what actually fixes it — Successful enterprise AI requires bridging foundational research with applied development and rigorous, continuous evaluation.
• The Production Gap: Your AI Model Isn’t as Reliable as You Think [Interview] — AI reliability in production demands system-level design for uncertainty and intent, not just model accuracy.

Open in AIssential →

Editorial summary, takeaway, and curation by AIssential. Original article published by InfoQ.