Building, troubleshooting, and managing Openshift / Kubernetes clusters sometime with GPUs.
I'm currently building:
- cluster-code - AI agent for K8s / OCP cluster management.
- llm-on-k8s - Production-grade LLM deployment on Kubernetes.
I would be more than happy to contribute and help companies host their own inference services, as I strongly believe this is crucial for product and service survival.



