ALL SPEAKERS
AT A GLANCE
Role
Developer Relations Engineer
Organisation
Exoscale
Category
Partner
ABOUT THE SPEAKER
Luc Juggery is a software engineer with experience in corporations, startups, and as a co-founder. He continuously develops his skills through side projects, online courses, and technical events as both speaker and attendee. His expertise spans Docker, Kubernetes, cloud-native technologies, DevOps, infrastructure as code, and CI/CD. Passionate about learning and knowledge sharing, he enjoys teaching and helping others adopt modern cloud-native practices.
TALK
The routing layers of an LLM inference stack
We have been using HTTP load balancers for ages to route external requests to workloads running in our Kubernetes Pods. First with Ingress Controllers, then with Gateway API. But should we use the same approach for AI workloads? In this talk, we'll follow an inference request and see how traditional load balancing evolves into AI-aware routing. Doing so, we'll explore the different routing layers of an AI inference stack through projects such as the Gateway API Inference Extension, vLLM Semantic Router, and llm-d. We'll see how an inference request is actually routed, taking into account the work it represents.
MORE VOICES
Other speakers at code.talks
See them live — and 100+ more.
One ticket, every track. Nov 4–5, 2026 at Kinopolis Hamburg.
Get your ticket





