Inference RoutingSummit
Where intelligence meets optimization. Join engineering leaders for intimate, off-the-record discussions about deploying AI in production and optimizing every inference call at scale.
Companies attending
Where intelligence meets optimization.
Building model access into production is easy. The hard part is matching each inference call with a model that optimizes token budget, capability and availability, while maintaining agent SLO and avoiding provider lock-in.
Join engineering leaders from Google, Hitachi, Broadcom, Composio, and more at the Inference Routing Summit, hosted by Tetrate, to learn how dynamic routing helps your organization optimize every inference call, at scale.
This curated gathering of leaders will feature intimate, off-the-record discussions about deploying AI in production.
Lunch and light snacks included. In person only, no livestream.
What We'll Cover
- AI traffic management at scale
- MCP and agent connectivity in production
- How enterprises are building their inference stack
Who Should Attend
CTOs, VPs of Engineering, and heads of platform, AI, and infrastructure who are responsible for their company's AI stack.
Speakers
Delyan Raychev
Cloud Infrastructure for AGI
OpenAI
Ian Cairns
Director of Product Management
NVIDIA
Guido Appenzeller
Partner
Andreessen Horowitz
Mandar Jog
Member of Technical Staff
xAI
Alex Salkever
Editor-in-Chief
AAIF (Agentic AI Foundation)
James Watters
VMware / Broadcom
Sesh Jalagam
Box
Sven Mawson
Chief Software Architect
Samba Nova
Milind Pathak
Sr. AI/ML Architect
Hitachi America
Soham Ganatra
Co-Founder
Composio
Tina Tsou
SVP, AI Ecosystem
Bitdeer
Varun Talwar
Co-Founder
Tetrate
Vaibhav Katkade
Group Product Manager
Google Cloud
Debojyoti (Debo) Dutta
Chief AI Officer
Nutanix
Johnu George
Technical Director, AI
Nutanix
John Landa
Tetrate
Milind Torney
Broadcom
Baldwin Mathew
Tetrate
Sachal Malick
NVIDIA
Nick DiZazzo
Product Architect
Tetrate
David Wang
Head of Product
Tetrate
Vinod Kone
Co-founder and CEO
Stacktrace
Yan Avlasov
Software Engineer
Google
Ignasi Barrera
Founding Engineer
Tetrate
Supporting Partners
Supporting partners
Agenda
02 / Nov 3Inference Routing Summit 2026
Nov 3 · SVB Experience Center, San Francisco- 9:00 AM
- 9:10 AMWelcome
Opening Remarks
Jeyappragash JJ · Tetrate - 9:20 AM
- 9:45 AMAI Frontiers
Google's approach to governing and optimizing Agents Everywhere with Envoy
Vaibhav Katada · Google Cloud - 10:10 AMAI Frontiers · Panel
Many Models, Many Clouds, Many Chips: Matching Inference Supply to Demand
James Watters · VMware / Broadcom; Ian Andrews · NVIDIA; Guido Appenzeller · a16z; Moderator: David Wang · Tetrate - 10:45 AM
Morning Break
- 11:00 AM
- 11:20 AM
- 11:45 AMEnterprise adoption
From Tokens to Value: Enterprise AI cost governance
Milind Pathak · Hitachi America - 12:10 PMSovereign AI and Private Inference in Enterprise
Customer lens on Sovereign AI and private inference
Debjyoti Dutta · Nutanix - 12:30 PM
- 12:45 PM
Lunch
- 1:35 PM
- 1:45 PMAgentRouter maintainers · Panel
What is next in the ecosystem
Yan Avlasov · Google; Ignasi Barrera · Tetrate; Johnu George · Nutanix; Moderator: Alex Salkever · AAIF - 2:20 PMEcosystem panel
Tools, Guardrails, Controls: Extending Agent Router
Soham Ganatra · Composio; Milind Torney · Broadcom; Vinod Kone · Stacktrace - 2:55 PM
Afternoon Break
- 3:10 PM
- 3:15 PMFrom Silicon to Inference · Panel
Inference at Scale: Smarter Routing for Cost, Quality, and Performance
Tina Tsou · Bitdeer; Mandar Jog · xAI; Sven Mawson · Samba Nova; Moderator: Matt Baldwin · Tetrate - 3:45 PMNvidia Dynamo · distributed inference with Envoy
From cluster to fleet: Global inference routing with Dynamo and Tetrate
Malick Sachal · NVIDIA; Varun Talwar · Tetrate - 4:15 PMAnnouncement: Smart Routing in Agent Router Enterprise
The Right Model for Every Request with Smart Routing
Nick DiZazzo · Tetrate; Ian Cairns · NVIDIA - 4:30 PM
- 4:35 PMReception
Drinks & Networking
- 6:05 PMEnd
End
Request to Attend
Join the room where production AI gets built.
If you're a CTO, VP of Engineering, or head of platform, AI, or infrastructure responsible for building and maintaining an AI stack in production, request access below.