
Self-hosted AI Stack on AWS EKS: Ollama + LiteLLM + Open WebUI
How I deployed a production-ready, self-hosted LLM stack on Kubernetes using Helm, Karpenter, and KEDA — with GPU auto-scaling and SSO out of the box.

How I deployed a production-ready, self-hosted LLM stack on Kubernetes using Helm, Karpenter, and KEDA — with GPU auto-scaling and SSO out of the box.

A practical walkthrough of every finding — idle EC2, oversized RDS, duplicate load balancers, and more — and exactly how we fixed each one.

Stop clicking through cloud consoles. Here's how I use Terraform and Terragrunt to manage scalable, cost-optimized AWS infrastructure.

Kubernetes can feel overwhelming at first. Here's a no-nonsense guide based on real production experience running EKS clusters at scale.

You can't fix what you can't see. Here's how I set up a full observability stack on EKS using Prometheus, Grafana, and the kube-prometheus-stack.

AWS bills can spiral fast. Here are the strategies I use in production to cut cloud costs without sacrificing performance or reliability.

ArgoCD changed how I think about deployments. Here's how to set up GitOps for your Kubernetes workloads — and why you won't go back to manual kubectl applies.

Automate your build, test, and deploy workflow using GitHub Actions — lessons learned from real production pipelines.