Senior OpenShift Platform Engineer - MLOps/LLMOps

Job description

Location : Remote.

Type : Full-Time.

Experience Level : Senior (Minimum 5+ years of relevant experience).

Industry : Cloud Infrastructure, AI/ML Ops, Kubernetes.

About the Role :

Were looking for a Senior OpenShift Platform Engineer with 5+ years of hands-on experience in OpenShift and Kubernetes.

In this strategic role, you'll lead the design and implementation of MLOps / LLMOps systems on OpenShift, mentor engineers, and help scale secure, high-performance AI infrastructure in collaboration with cross-functional teams.

Key Responsibilities :

Platform Leadership :

- Architect, install, upgrade, and manage OpenShift clusters, both on bare metal and VMware.

- Implement production-grade solutions for model deployment, monitoring, and validation pipelines.

Infrastructure Excellence :

- Set up robust monitoring (Prometheus, Thanos, Grafana), logging, and backup strategies.

- Ensure secure and efficient configurations for RBAC, networking, and persistent storage (NetApp preferred).

Collaboration & Communication :

- Translate customer and product requirements into technical solutions.

- Mentor team members and promote a high standard of engineering practices.

Incident Management & Governance :

- Own and lead root cause analysis (RCA) and post-mortem follow-ups.

Must-Have Qualifications :

- Minimum 5 years of experience in OpenShift cluster installation, management, and lifecycle operations.

- Hands-on experience with bare metal or VMware-based OpenShift deployments.

- Deep understanding of Kubernetes/OpenShift security, RBAC, networking, and persistent storage (NetApp preferred).

- Expertise in setting up monitoring, logging, and backup solutions.

- Proficiency with CI/CD DevOps tools such as GitLab and ArgoCD.

- Solid experience with observability tools like Prometheus, Thanos, and Grafana.

- Strong communication and presentation skills to engage both technical and non-technical stakeholders.

- Ability to juggle multiple projects and deliver with minimal oversight.

Bonus Skills (Highly Desirable) :

- Experience with OpenShift AI and deployment of MLOps/LLMOps workflows.

- Open-source contributions in Kubernetes/MLOps communities.

- Experience leading customer-facing technical discussions and workshops.