Openshift AI Ops Consultant

TEKsystems • Pennington, NJ

1d • $80 - $90 • Hybrid

About The Position

We’re seeking a senior AI Platform SRE / MLOps engineer to support and stabilize a production Generative AI platform, running on Red Hat OpenShift. This is a hands-on, high-impact role focused on operational excellence, reliability engineering, and performance tuning of GPU-accelerated AI workloads in a regulated enterprise environment. You will act as a key technical resource within Dell’s delivery team, helping bring structure, stability, and scalability to an evolving GenAI platform.

Requirements

• 8+ years in SRE / DevOps / Platform Engineering roles
• Deep experience with Red Hat OpenShift or Kubernetes in production environments
• Cluster administration, scaling, upgrades, troubleshooting
• Hands-on experience supporting AI/ML workloads in production
• Proven experience with GPU-accelerated environments, including: NVIDIA stack (CUDA, Triton, TensorRT, etc.)
• Strong SRE mindset: Incident management, monitoring, uptime, reliability engineering
• Scripting/automation experience (Python, Bash, etc.)
• Ability to operate independently in ambiguous, high-pressure environments

Nice To Haves

• Experience in financial services or regulated environments
• Familiarity with MLOps tooling (Kubeflow, MLflow, ArgoCD)
• Knowledge of model optimization techniques (quantization, pruning)
• Certifications: Red Hat (RHCE), CKA / CKS
• Prior consulting or residency-style engagements

Responsibilities

• Own day-to-day operations of a production GenAI platform running on OpenShift/Kubernetes
• Diagnose and resolve performance, stability, and scaling issues across AI workloads
• Optimize GPU-based inference pipelines using tools like: NVIDIA Triton Inference Server, TensorRT / CUDA
• Implement SRE best practices: Monitoring & observability (Prometheus, Grafana, etc.), Incident response & root cause analysis, Automation & runbook creation
• Improve cluster performance, resource utilization, and reliability
• Collaborate with stakeholders while operating with high autonomy and limited guidance
• Ensure platform adheres to enterprise governance, security, and compliance standards

Benefits

• Medical, dental & vision
• Critical Illness, Accident, and Hospital
• 401(k) Retirement Plan – Pre-tax and Roth post-tax contributions available
• Life Insurance (Voluntary Life & AD&D for the employee and dependents)
• Short and long-term disability
• Health Spending Account (HSA)
• Transportation benefits
• Employee Assistance Program
• Time Off/Leave (PTO, Vacation or Sick Leave)

What This Job Offers

• Job Type: Full-time
• Career Level: Senior
• Education Level: No Education Listed