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

AI Native Netherlands convenes this Amsterdam engineering meetup at AWS for a practical look at deploying AI inference beyond a default GPU-backed LLM setup. Christian Melendez of AWS will cover selecting CPUs, GPUs, small language models and larger models for a production pipeline on Kubernetes, including cost and performance trade-offs.

William Rizzo of Mirantis will then examine LLM inference on immutable, disconnected edge clusters used in environments such as factories, vehicles and retail sites. Arrival, food and drinks begin at 18:00; the two talks start at 18:45 and 19:30, followed by open conversation and networking. The session is suited to ML, platform and infrastructure engineers working on real AI systems.