Inference Routing Summit
- WHO IT IS FOR: Senior engineering leaders and AI practitioners responsible for building and maintaining production-scale AI stacks.
- WHAT IT IS ABOUT: Exploring dynamic inference routing to optimize token budgets, model capability, and provider availability.
- FORMAT: A full day of in-person keynotes, panel discussions, and intimate off-the-record talks.
The Inference Routing Summit brings together the industry's brightest minds to solve the most pressing challenges in AI production. While deploying models is simple, managing them at scale requires sophisticated strategies to balance token budgets, model capability, and agent SLOs while avoiding provider lock-in. This summit dives deep into the intersection of intelligence and optimization, focusing on how to build a resilient inference stack.
Join leaders from Google, OpenAI, xAI, NVIDIA, and more for a curated, in-person gathering at the SVB Experience Center in San Francisco. Attendees will explore real-world applications of AI traffic management, MCP connectivity, and enterprise-grade infrastructure. This is a unique opportunity to engage in high-level, off-the-record discussions with 100 senior leaders driving the next wave of agentic AI.