Role: OpenShift Systems Operations Engineer and Agentic AI Developer Focus
Location: Dallas, TX, Charlotte, NC, or Chandler, AZ - Hybrid
Exp: 10+
Duartion: 18 Months + Possible Extension
Employment: W2
Interview mode: Virtual + F2F
Advanced OpenShift Engineering & Operations ( 4 to 6 years)
o Deep expertise with OpenShift includes building clusters with pipelines, diagnosing, debugging, remediation, upgrades, patching, and RCA.
o Strong experience with Operators, Diagnostics hub operators, ETCD, API server, OVN K networking, workloads, and cluster internals.
Python development and OCP API skills for Remediation & Automation tasks (> 5 years)
o Strong, production-quality Python engineering skills.
o Hands-on experience with the OpenShift Python client and Operator / Kubernetes Python libraries.
o Ability to build automated remediation workflows and operational tools in Python.
o High code quality Unit Tests, Vulnerability Management
o Packaging and Deploying Experience Helm Charts, CI/CD, GitSaaS workflows
o System Design Experience
o Technical Documentation
Agentic AI Development for OCP ( > 3 years)
o Experience developing agentic AI workflows aimed at OpenShift operations and remediation.
o Strong skills with frameworks such as LangChain, Google ADK/Agents, or similar multi agent orchestration tools.
o Develop skills and Tools for Agentic AI to complete tasks for OpenShift Platform
o Ability to build tool calling agents that interact with OpenShift safely and deterministically.
o Experience building agentic AI systems without using managed ML/AI platforms such as AWS SageMaker, Bedrock, Vertex AI, or similar hosted orchestration services.
** Candidate should have developed and deployed self-hosted, Python-based AI/agentic services end to end.
API Automation Platform (FastAPI / Flask)
o Ability to build, extend, and maintain a Python-based automation platform (FastAPI or Flask) that executes OpenShift actions.
o Experience designing agent tools/endpoints for AI-driven workflows.