Renen Hallak
CEO, VAST Data
Deploy San Francisco
The Conference for the Inference Era
The Conference for the Inference Era
April 28, 2026
San Francisco - Convene 100 Stockton
12:00pm - 8:00pm PT
Mainstage keynote streamed liveReal companies.
Real inference workloads.
Running today.
Join leaders from Character, Workato, VAST Data, Arcee, and the vLLM ecosystem as they break down how they are running AI in production at scale.
You'll hear directly from:
- Renen Hallak (CEO, VAST Data)
- Simon Mo (CEO, Inferact)
- Mark McQuade (CEO, Arcee)
- James Groeneveld (Chief Architect, Character.ai)
- Oscar Wu (AI Research Technical Lead, Workato)
- Dan Grosu (CTO/CISO, ISMG)
The hardest problem in AI is no longer training models. It's running inference in production: latency, throughput, system reliability, and unit economics, all at once.
Deploy is where you will see how leading AI-native companies solve this, through real architectures, real tradeoffs, and live systems running today.
Across sessions and hands-on demos, you'll learn how teams are designing inference systems that scale without breaking performance or their margin structure.
Why Attend Deploy
- See How Real AI Companies Run Inference at Scale Hear from companies already running inference at scale and learn how they handle spiking traffic, latency constraints, and real cost pressure.
- Learn the Architecture Behind Built-for-Scale AI Products Routing, batching, caching, autoscaling, quantization, and GPU orchestration. Learn how these systems fit together effectively in real production stacks.
As workloads shift toward multimodal and agentic loops, the teams that win will be the ones who design the right systems around their models. - Control the Economics of AI Products If you can't deliver high inference performance with predictable unit costs at scale, you don't have a product. You have a burn rate.
Walk away with practical frameworks to improve TTFT, tail latency, throughput per GPU, and cost per outcome without getting surprised by volatility, egress, or runaway retries. - Meet the Teams Building the Next Generation of AI Products Connect with founders, CTOs, and engineering leaders running AI systems in production today. Compare approaches, share lessons learned, and connect with peers solving the same challenges of scaling inference reliably and cost-effectively.
Meet the Speakers
Simon Mo
CEO, Inferact
Mark McQuade
CEO, Arcee
James Groeneveld
Chief Architect, Character.ai
Paddy Srinivasan
CEO, DigitalOcean
Oscar Wu
AI Research Technical Lead, Workato
Dan Grosu
CTO/CISO, ISMG
Vinay Kumar
CPTO, DigitalOcean
Laura Schaffer
Head of Growth & Marketing, DigitalOcean
Meghan Grady
Senior Director, Marketing & Communications, DigitalOcean
Archana Kamath
VP of Engineering, DigitalOcean
Piyush Srivastava
Principal Engineer, DigitalOcean
Philip Reichenberger
Senior Director of AI/ML, DigitalOcean
Debarshi Raha
VP/Fellow Engineer, DigitalOcean
Karthik Pandian
Senior Director of Engineering, DigitalOcean
Dinesh Murthy
Director of Product Management, DigitalOcean
Agenda at a Glance
Optimizing AI Unit Economics
Learn how leading teams optimize inference performance and cost in production — including intelligent routing, benchmarking, and cost-per-token optimization to protect unit economics at scale.
Speakers:
Archana Kamath (VP, Engineering, DigitalOcean)
Piyush Srivastava (Principal Engineer, DigitalOcean)
Oscar Wu (AI Research Technical Lead, Workato)
Shipping AI Features at Speed
Don't let infrastructure stall your roadmap. See how teams integrate and ship production-ready AI features into existing applications using smart defaults, streamlined workflows, and scalable architecture patterns.
Speakers:
Philip Reichenberger (Senior Director, AI/ML, DigitalOcean)
Shipra Mishra (Director, Product Management, DigitalOcean)
Dan Grosu (CTO/CISO, ISMG)
Building a Production-Ready AI Stack
AI belongs in your stack, not in a silo. Learn how teams are integrating security, data infrastructure, vector databases, and observability into unified production systems for AI workloads.
Speakers:
Karthik Pandian (Sr. Director of Engineering, DigitalOcean)
Dinesh Murthy (Director of Product Management, DigitalOcean)
Inference Systems Deep Dive
A technical deep-dive into modern inference architecture — from serverless to dedicated GPUs, containerized services, and intelligent routing systems that power high-performance production AI.
Speakers:
Debarshi Raha (VP, Fellow Engineer, DigitalOcean)
Simon Mo (CEO, Inferact)
The Deploy 2026 agenda is taking shape — check back in for some more exciting updates! Across sessions, expect live demos and hands-on examples showing how these systems actually run in production.
Secure your seat in San Francisco
April 28, 2026 • 12:00pm – 8:00pm PT
📍 Convene 100 Stockton
Join the technical leaders and executives building the next generation of AI-native companies at Deploy, the Conference for the Inference Era.
Drinks are on us at the AI Builder's Mixer
Close out Deploy with the people building the future of AI. At 5pm, join the AI builder community for a casual mixer with demos, networking and more.
FAQ
When and where is Deploy?
Deploy 2026 will be hosted in person at Convene 100 Stockton, 40 O'Farrell St, San Francisco. The mainstage keynote will also be streamed live to registrants.
Who should attend Deploy?
Deploy is designed for teams responsible for managing or building AI workloads in production at scale.
Why should I attend Deploy?
This is a special Deploy that represents an evolution of cloud infrastructure that will change the way companies with AI in production conceive of their businesses. DigitalOcean's vertically integrated agentic inference cloud delivers radically simple operations and predictable unit economics that will set AI-natives on a path to success and growth.
Is there a cost to attend?
No. Deploy is free to attend. See you in San Francisco.
Is there a code of conduct?
Yes. Deploy follows the DigitalOcean Community Code of Conduct.