OpenShift Systems Operations Engineer / Agentic AI Developer

OpenShift Systems Operations Engineer / Agentic AI Developer

Location: Charlotte, NC | Dallas, TX | Phoenix, AZ

Work Model: Hybrid (3 days onsite)

Duration: 12-Month Contract (Potential conversion to FTE after 6 months)

Overview

We are seeking an experienced OpenShift Systems Operations Engineer with strong Python development skills and experience building Agentic AI systems to support advanced platform automation and remediation initiatives. This role combines deep OpenShift platform engineering expertise with AI-driven automation, enabling intelligent operational tooling that improves reliability, diagnostics, and automated remediation across enterprise container platforms.

The ideal candidate has hands-on experience operating and engineering OpenShift clusters at scale, building Python-based automation platforms, and developing self-hosted agentic AI systems that interact with infrastructure environments through APIs and tools.

This role will help design and build AI-driven operational workflows that enhance observability, automate remediation, and streamline OpenShift platform management.

Key Responsibilities

OpenShift Platform Engineering & Operations

• Design, build, and maintain enterprise OpenShift clusters and platform infrastructure
• Perform advanced diagnostics, troubleshooting, and root cause analysis (RCA) for cluster and workload issues
• Manage cluster lifecycle operations, including upgrades, patching, remediation, and performance optimization
• Work with core OpenShift components including:
• Operators
• Diagnostics Hub Operators
• ETCD
• API Server
• OVN-K Networking
• Workload scheduling and cluster internals
• Develop and maintain automation pipelines for platform management and deployment

Python Development for Automation & Remediation

• Build production-grade Python automation tools for OpenShift platform operations
• Develop automated remediation workflows using:
• OpenShift Python Client
• Kubernetes Python libraries
• Create operational tooling to support monitoring, diagnostics, and infrastructure management
• Maintain high-quality engineering practices, including:
• Unit testing
• Vulnerability management
• Code reviews
• Documentation
• Package and deploy solutions using Helm charts, CI/CD pipelines, and Git-based workflows
• Participate in system architecture and technical design decisions

Agentic AI Development for Platform Operations

• Design and develop agentic AI workflows to automate OpenShift operations and remediation tasks
• Build tool-calling AI agents that interact with OpenShift APIs safely and deterministically
• Implement multi-agent orchestration using frameworks such as:
• LangChain
• Google ADK / Agents
• Similar agent orchestration frameworks
• Develop AI tools capable of:
• Cluster diagnostics
• Automated remediation
• Operational task execution
• Build and deploy self-hosted Python-based AI services end-to-end without reliance on managed ML platforms
• Integrate AI agents with internal automation platforms and APIs

API Automation Platform Development

• Design and maintain a Python-based automation platform using:
• FastAPI
• Flask
• Develop APIs that allow AI agents and operational tools to perform OpenShift actions
• Build reusable service endpoints that support automation, diagnostics, and platform management
• Ensure platform security, reliability, and scalability

Required Qualifications

• 4–6 years of OpenShift engineering and platform operations experience
• 5+ years of Python development experience
• 3+ years of experience developing agentic AI systems
• Strong expertise with:
• OpenShift cluster architecture
• Kubernetes internals
• Cluster lifecycle management
• Hands-on experience with:
• OpenShift Python client
• Kubernetes Python libraries
• Helm charts
• CI/CD pipelines
• Git-based workflows
• Experience designing automation systems for infrastructure remediation
• Experience building self-hosted AI/agent systems in Python