Laboringenieur*in mit Schwerpunkt Clusterbetrieb (m/w/d) / 065/26
Core
Operating, maintaining, and evolving Bare-Metal Kubernetes infrastructure for a university lab, including cluster nodes, Linux servers, and Large-Language-Model applications.
Role type
Senior Infrastructure Engineer (Kubernetes & LLM Ops)
Builds
Bare-Metal Kubernetes clusters, LLM inference services, and observability pipelines for a university research and teaching environment.
Domain
Higher Education / Cloud Infrastructure / AI Infrastructure
Deliverable
production ML models
Required skills
Kubernetes cluster administration, Linux server management, LLM application deployment (vLLM, Streamlit), observability (Prometheus, Grafana, Jaeger, OpenTelemetry), network infrastructure (VLANs, Routing, DNS, DHCP, Firewalls), virtualization and storage (Proxmox, Ceph)
Preferred skills
None stated
Technologies
Kubernetes, Linux, vLLM, Streamlit, Prometheus, Grafana, Jaeger, OpenTelemetry, Proxmox, Ceph
Responsibilities
Operate and maintain Bare-Metal Kubernetes infrastructure; Deploy and monitor Large-Language-Model applications; Build and manage tracing, monitoring, logging, and alerting structures; Manage lab network infrastructure (VLANs, Routing, DNS, DHCP, Firewalls); Collaborate with students and faculty.
Seniority
Senior, hands-on IC
