Serving an LLM on Kubernetes: slow starts, heavy weights and the right scaling signal.
Why a model server breaks the defaults you use for web apps, and how to set probes, model storage, autoscaling and routing for AI inference.
THE NOTEBOOK
A little less theory.
A little more doing.
Clear explanations, practical checklists, and things worth remembering the next time you open a terminal.
A GPU is not a bigger CPU. Schedule it like one and your pod waits.
How Kubernetes actually allocates GPUs to AI workloads: whole devices, taints, sharing with isolation in mind, and Dynamic Resource Allocation.
An inference platform on Azure starts with the gateway, not the GPU.
How to choose where models run on Azure, and the shared front door that turns them into a platform: identity, token limits, failover and cost per team.
Treat AI agents as platform tenants, not scripts.
What a platform team should give AI agents before they reach real tools, and three real incidents that show what happens without it.
Your pod is stuck. Here's where to look first.
A calm, practical checklist for debugging Kubernetes pods—before you reach for another restart.
Read the Terraform plan, not just the green check.
A small review routine for spotting replacements, unexpected drift, and changes that deserve a second look.
A useful tech blog doesn't need a server.
Why a Markdown-first, static publishing workflow is a good starting point for a personal engineering blog.
Choose your next course by the thing you want to build.
A simple way to turn a long course wishlist into a learning plan you can actually finish.