AI Infrastructure & Cloud Engineer

Requirements:

• At least 5 years of experience in infrastructure, cloud, DevOps, or platform engineering, including enterprise production environments.
• At least 2 years administering Kubernetes and deploying containerized Linux workloads.
• Practical experience with Azure virtual networks, virtual machines, AKS, security, and monitoring.
• Strong Linux troubleshooting and networking fundamentals, including TLS, DNS, access controls, and API connectivity.
• Hands-on experience with Terraform, Ansible, scripting, Git, and CI/CD.
• Clear documentation skills, independent problem-solving ability, and effective collaboration with technical and commercial teams.
• Helpful additional experience includes NVIDIA GPUs, CUDA, vLLM, NVIDIA NIM, open-weight LLMs, inference benchmarking, AI gateways, runtime security, Microsoft Entra ID, SSO/RBAC, Prometheus, Grafana, Log Analytics, VMware, Dell PowerEdge, private or hybrid infrastructure, FinOps, API consumption reporting, or enterprise data-access governance.
• Relevant Azure, CKA, Terraform, VMware, or NVIDIA certifications are welcome. Experience with every listed AI product is not required; strong Azure, Kubernetes, Linux, networking, and automation skills are the foundation, along with an ability to learn new infrastructure technologies.

Responsibilities:

• Design and operate Azure infrastructure, including compute, networking, AKS, identity, security, storage, and monitoring.
• Deploy containerized services with Kubernetes, Docker, and Helm, using Git-based delivery and CI/CD practices.
• Automate provisioning and configuration with Terraform, Ansible, and scripting, and maintain reusable deployment templates.
• Deploy and support vLLM on Linux GPU systems, including quantized models up to 10B parameters for the lab; troubleshoot NVIDIA drivers, CUDA, memory use, and serving performance.
• Integrate Open WebUI, enterprise authentication, CPU-based AI gateways, and secrets management; validate secure model routing and access policies.
• Monitor latency, concurrency, GPU utilization, API errors, and infrastructure costs, and develop alerting, recovery procedures, and runbooks.
• Prepare architectures for transition from Azure to local Kubernetes and GPU environments on Dell/VMware infrastructure.
• Support customer proofs of concept and demonstrations, document operational handoffs, and work with MSP teams on production readiness.

Technologies:

• AI
• API
• Ansible
• Azure
• CI/CD
• Cloud
• CUDA
• DevOps
• Docker
• Git
• Grafana
• Helm
• Support
• Kubernetes
• Linux
• Prometheus
• RBAC
• Security
• Terraform
• VMware
• vLLM

More

We are Unified Technologies, growing our AI & Cloud Solutions practice. In this hands-on AI Infrastructure & Cloud Engineer role, you will help build our Azure AI Lab into repeatable customer demonstrations, proofs of concept, and managed infrastructure services, working with architecture, presales, security, and MSP teams to reproduce platforms across cloud and on-premises environments. The focus is on cloud infrastructure, CPU-based Kubernetes services, GPU inference, and operational reliability. Compensation is $150,000–$200,000 per year. Benefits include dental, health, life, and vision insurance, a health savings account, a flexible schedule, and paid time off. This is an in-person position.

last updated 43 week of 2026