Pulin

@blue_spinnaker

GPU Infrastructure LLMOps Engineer NVIDIA Kubernetes Neo Cloud

United States

English

About me

I build scalable NVIDIA GPU infrastructure for AI training and inference. I specialize in Kubernetes GPU clusters, LLM training/inference, and GPU observability. Services: • GPU cluster setup • Kubernetes GPU orchestration • vLLM / Triton / Ollama optimization • GPU monitoring with DCGM + Prometheus / Grafana • Terraform automation • AWS / Azure / GCP deployments Tech Stack: NVIDIA, CUDA, Kubernetes, Helm, Terraform, Prometheus, Grafana... Read more

Skills