AI Inference in the Real World: From Kubernetes to the Far Edge

The 13th AI Native Netherlands meetup, hosted at AWS's Amsterdam office, on a single engineering question: what should run where, on what hardware, and how do you keep it reliable in production. Christian Melendez, Principal Specialist Solutions Architect at AWS and author of Kubernetes Autoscaling, makes the case for CPUs and small language models on the structured, high-frequency work - classifying, routing, embedding, reranking - with a live pipeline demo. William Rizzo of Mirantis takes the same question to the far edge: LLM inference on immutable, disconnected clusters in factories, vehicles and retail sites, where connectivity is unreliable and remote access cannot be assumed. 18:00 to 21:00, with food and drinks provided by the host. Free. RSVP on Meetup in advance. Why go: a rare evening about cost and constraint engineering rather than model hype, from two people who run this in production. Best for platform and ML engineers weighing a GPU bill against a smaller model.