OpenShift Engineer - AI Platform (Red Hat AI Operator)
Job Description
OpenShift Engineer – AI Platform (Red Hat AI Operator)
\n
Role Summary:
\n
Seeking an experienced OpenShift Engineer with expertise in deploying and managing AI/ML applications on Red Hat OpenShift. The candidate should have hands-on experience with Red Hat OpenShift AI (RHOAI), Red Hat AI Operators, Kubernetes, GPU-enabled environments, and MLOps platforms.
\n
Key Responsibilities:
\n
• Deploy, administer, and optimize OpenShift clusters for AI workloads.
\n
• Install and manage Red Hat AI Operators and OpenShift AI components.
\n
• Support AI model training, serving, and inference environments.
\n
• Manage GPU-based infrastructure using NVIDIA GPU Operator.
\n
• Automate deployments using GitOps, ArgoCD, Ansible, and Terraform.
\n
• Monitor, troubleshoot, and ensure platform security and performance.
\n
Required Skills:
\n
• Red Hat OpenShift (OCP) 4.x
\n
• Red Hat OpenShift AI (RHOAI) / Red Hat AI Operator
\n
• Kubernetes, Docker/Podman
\n
• AI/ML platform operations and model serving
\n
• NVIDIA GPU Operator and GPU workload management
\n
• ArgoCD, GitOps, Ansible, Terraform
\n
• Linux (RHEL) Administration
\n
Preferred:
\n
• Experience with GenAI/LLM deployments, KServe, ModelMesh, and MLOps platforms.
\n
• OpenShift or Kubernetes certifications.