The F5 AI Summit (June 23–25) is focused on one thing: what it takes to run AI in production without things falling apart.
If you’re building or operating AI apps, expect practical sessions around the parts that usually cause problems—data flow, security, and scaling.
Registration is free and if you follow DevCentral, you’ll be sure to see some familiar faces presenting!
TL;DR
Here are a few things you’ll learn at the AI summit:
- How to design AI architectures that connect data, models, and traffic in a way that actually works at scale
- Where performance bottlenecks really live (hint: the data path, not just the model)
- How to secure AI systems with guardrails, policies, and continuous testing
- What it takes to scale inference—including GPU utilization and traffic control
- How to run AI on Kubernetes with routing, observability, and policy built in
Agenda Highlights
Here are details for some of the sessions you won’t want to miss… especially the ones from rockstar DevCentral contributors!
The Right Ecosystem for Secure AI
Buu Lam will moderate a discussion with Ugur Tigli (CTO of MinIO) and Leon Derczynski (Principal Research Scientist at NVIDIA) to break down how cross-vendor architectures are shaping real-world AI deployments.
- Find out how integrating storage (MinIO), compute (NVIDIA), and application delivery/security layers enables faster data pipelines and more controlled inference flows.
- Get insights into AI data movement, system interoperability, and runtime security, especially how partnerships can help close gaps between infrastructure components.
Reliability Between Compute and Storage
Hunter Smit and Mark Menger walk through why data delivery is now the critical layer in AI infrastructure, especially as workloads shift from training to production inference.
- Learn how keeping pipelines efficient under load—covering how to optimize data paths so GPUs stay utilized and avoid idle time.
- See the role of application delivery controllers (ADCs) as a control point for storage traffic (including S3), acting as a front door for AI data movement.
Delivering AI on Kubernetes: Model-Aware Routing and Traffic Control with NGINX
Michael Kingston focuses on how to run AI workloads on Kubernetes with routing and traffic control designed specifically for inference workloads, highlitings capabilities like model-aware routing and policy enforcement, along with updates to NGINX Gateway Fabric and alignment with Gateway API standards.
- Get a practical look at how to add observability and control at the ingress layer, giving teams better visibility into AI traffic and more consistent behavior in production environments.
- See how to turn Kubernetes into a reliable control plane for AI inference.
Conclusion
Expect a more complete picture of the AI stack—from infrastructure and networking to security and runtime behavior.
Registration is free!If you’re responsible for making AI systems reliable, fast, and secure in production, this will give you information you can actually apply.