Expert Site Reliability Engineer - Edge Infrastructure (f/m/d)

Expert Site Reliability Engineer - Edge Infrastructure (f/m/d)

Engineering · Munich · Remote · FullTime · Senior level

The role asks for deep hands-on ownership of edge infrastructure: server hardware, Linux, networking, and GPU enabled Kubernetes running at customer sites. A strong candidate brings proven automation of bare metal provisioning with Terraform, solid monitoring and incident response skills, and fluency in Go or Python. The job is an individual contributor expert track, so it rewards someone who can set technical direction and mentor others without formal management.

How it fits the AI era

AI changes the work by making the edge fleet larger and more automated, so reliability engineering leans on infrastructure as code and proactive observability. The human core stays in architecture decisions, incident triage, and post incident reviews that turn failures into lasting fixes. Physical hardware and secure networks still need a person who understands them deeply.

How it builds AI experience

The role offers direct experience running GPU enabled Kubernetes for AI classification services at the edge, close to Orbem's MRI and computer vision work. Building that experience means practicing bare metal automation, GitOps delivery, and observability for unattended systems. Familiarity with how AI workloads stress hardware and networks would be useful to develop.

Worth showing

• Linux and server hardware
• Prometheus and Grafana
• Go or Python

This is our own read, written from the employer's posting and the company's Spotlight. The employer's posting is the source of truth for the role.

About Orbem

Orbem develops high-throughput magnetic resonance imaging hardware and artificial intelligence algorithms that non-invasively inspect poultry eggs and agricultural produce.