Multi-cloud Terraform deployment framework for the vLLM Production Stack — with implementations for AWS (EKS), Azure (AKS), GCP (GKE), Nebius, and Oracle OKE.

Production-ready Kubernetes project for GPU-backed AI inference (vLLM, OpenAI-compatible API) on CoreWeave Kubernetes Service — Kustomize overlays, RWX storage, GPU node scheduling, NGINX ingress with TLS.

PyTorch + Weights & Biases demo project for CoreWeave AI Solutions Engineer role

Ansible Collection for CoreWeave GPU cloud