MLOps / Platform Engineer (m/w/d)
Core
Build and operate the infrastructure behind AI systems, focusing on Kubernetes-based services for LLM serving, workflow automation, and GPU workloads.
Role type
MLOps / Platform Engineer (Kubernetes/DevOps)
Builds
Central cluster services (n8n, LiteLLM), MCP-Server, CI/CD pipelines, and GPU/LLM-serving infrastructure.
Domain
AI/ML Infrastructure, Cloud Native, Kubernetes
Deliverable
production ML models | infrastructure
Required skills
Kubernetes, DevOps, CI/CD, GitOps, Linux, Networking, Observability, LLM Gateway configuration, GPU workload management
Preferred skills
Ray, GPU infrastructure, LLM Serving, Prometheus, Grafana, Loki, cert-manager, DNS management
Responsibilities
Operate and maintain central cluster services (n8n, LiteLLM), develop and run MCP-Server, improve platform services (Ingress, Certificates, Secrets), build CI/CD and GitOps pipelines, integrate new services into the cluster, monitor production services and resolve incidents, support GPU workloads and LLM serving infrastructure.
Seniority
Mid-Senior, hands-on IC