Back
Specialized on-prem GPU and OpenShift MLOps skills reduce applicant pool despite mid-level seniority.
Highly domain-specific MLOps, on-prem GPU, and OpenShift experience limit cross-industry portability.
Extensive mandatory tech stack and 6+ years of MLOps/on-prem platform experience tightens shortlisting.
Login to See Your Match Score
Create a free account or log in to unlock your CV match score across:
Own end-to-end architecture, deployment, and scaling of on-prem AI/ML platforms including data pipelines and production monitoring.
Design and manage CI/CD pipelines, containerization (Docker/Kubernetes/OpenShift), and infrastructure for ML/LLM models on GPU-enabled systems.
Ensure production reliability, observability (Prometheus, Grafana, ELK), and lead technical mentorship and cross-team collaboration.
6+ years experience in MLOps, DevOps, or Platform Engineering.
Strong skills in Python, Bash scripting, Linux (preferably RHEL), Docker, Kubernetes/OpenShift, and CI/CD tools (Jenkins/GitLab CI).
Experience deploying ML/LLM models on on-prem GPU infrastructure with real-time and batch data integration using Kafka.
Must understand and explain AI/ML platform architecture, OpenShift AI ecosystem, and container orchestration; knowledge of SQL and data pipelines mandatory.
Senior-level hands-on platform architect comfortable managing both ML systems and underlying infrastructure.
Experienced in scaling production ML systems in restricted or air-gapped enterprise environments.
Able to clearly explain complex integration patterns (Kafka, Gunicorn) and drive automation and best practices for scalable, secure ML platforms.