On-Prem GenAI Engineer - OpenShift & GPU Expert

petrus.sa; Riyadh; On-site; SAR 260,000 - 420,000; Full time

Benefits offered by this job

On-site role in Riyadh

Job summary

petrus.sa is seeking an exceptional Forward Deployed AI Engineer in Riyadh to install, optimize, and integrate on-prem GenAI platforms within client banking environments. You will work hands-on with OpenShift, Kubernetes, and NVIDIA NIM, delivering secure, GPU-accelerated AI deployments in air-gapped networks.

The role emphasizes GitOps pipelines, strict SLA-driven model inference, and collaboration with client IT and security teams to maintain compliance and resilience in enterprise AI delivery.

Qualifications

• 4+ years software engineering or DevOps experience.
• 2+ years in MLOps/LLMOps deploying containerized apps in air-gapped environments.
• Hands-on Red Hat OpenShift or Kubernetes admin experience.
• Experience with NVIDIA NIM, DataRobot, Graph DBs is preferred.
• GitOps with ArgoCD/OpenShift Pipelines; Helm/Kustomize used for configs.

Responsibilities

• Install, configure, and optimize enterprise AI systems on-premises in client networks.
• Deploy NVIDIA NIM, LLMs, DataRobot, and Graph Databases on OpenShift/Kubernetes clusters.
• Package and deploy large container images and model weights into isolated environments.
• Tune OpenShift pods, configure MIG, and optimize local model inference for SLAs.
• Build automated GitOps pipelines (ArgoCD/OpenShift Pipelines) for deployment/rollback.
• Interface with client IT/security to remove deployment blockers and ensure compliance.
• Manage secret storage and enterprise authentication (Vault/OpenShift Secrets).

Skills

MLOps

LLMOps

OpenShift

Kubernetes

NVIDIA NIM

GPU optimization

GitOps

Containerization

Python/Go

Tools

ArgoCD

OpenShift Pipelines

NVIDIA GPU Operator

Kustomize

Helm

Git

Job description

petrus.sa is seeking an exceptional Forward Deployed AI Engineer in Riyadh to install, optimize, and integrate on-prem GenAI platforms within client banking environments. You will work hands-on with OpenShift, Kubernetes, and NVIDIA NIM, delivering secure, GPU-accelerated AI deployments in air-gapped networks.

The role emphasizes GitOps pipelines, strict SLA-driven model inference, and collaboration with client IT and security teams to maintain compliance and resilience in enterprise AI delivery.