I'm a platform, DevOps, and SRE engineer. I deploy and operate AI systems reliably in production — the infrastructure they run on, with the same reliability discipline you'd put behind any critical service.
That's a deliberate distinction. I'm not building AI features or training models; I'm the person who keeps agentic systems and LLM workloads running 24/7 — observable, cost-controlled, and dependable. Most of my two decades has been on AWS, with a homelab where I run the same patterns end to end: containerized services, full Grafana/Prometheus/Loki observability, and supply-chain security from build to signed artifact.
This site is where I keep the projects that show that work. Have a look around.