AI Infrastructure Lead - GPUs, Kubernetes & MLOps

Axiom Global Technologies; United States; Remote; USD 180,000 - 240,000; Full time

Job summary

Axiom Global Technologies seeks an AI Infrastructure Engineer to own GPU fleets, model serving, and Kubernetes clusters in the US and India. You will drive deployment paths, reliability, and cloud cost controls while maintaining on-call ownership of critical services.

Ideal candidates have deep CUDA/GPU fundamentals, vLLM production experience, and strong Python/Shell skills. Expertise in Azure AKS, Prometheus/Grafana, and PostgreSQL is highly valued.

Qualifications

• GPU-backed model inference running in production on Kubernetes with on-call ownership.

Responsibilities

• Owns the GPU fleet, model serving, the Kubernetes clusters in the US and India, the deploy path, reliability, and cloud cost.

Skills

GPU inference in prod

Kubernetes

Python

Shell

Terraform IaC

On-call ownership

vLLM

PyTorch

Prometheus Grafana

Azure AKS

Tools

Nsight

CUDA toolkit

PostgreSQL

CI/CD

Docker

KEDA

Job description

Axiom Global Technologies seeks an AI Infrastructure Engineer to own GPU fleets, model serving, and Kubernetes clusters in the US and India. You will drive deployment paths, reliability, and cloud cost controls while maintaining on-call ownership of critical services.

Ideal candidates have deep CUDA/GPU fundamentals, vLLM production experience, and strong Python/Shell skills. Expertise in Azure AKS, Prometheus/Grafana, and PostgreSQL is highly valued.