Expert Site Reliability Engineer - Edge Infrastructure (f/m/d)
Core
Own the reliability, availability, and performance of a global fleet of edge infrastructure (hardware, network, OS, Kubernetes) running AI classification services at customer sites.
Role type
Senior IC Site Reliability Engineer (Edge Infrastructure)
Builds
Edge racks, server hardware, network equipment, custom Linux-based OS, GPU-enabled Kubernetes layer, automation for provisioning 50+ edge clusters.
Domain
Industrial AI / Edge Computing / Hardware Infrastructure
Deliverable
production ML models
Required skills
Kubernetes, Golang or Python, Prometheus, Terraform, Linux, Server Hardware, GitOps (Argo CD), Security (IPSec/VPN, Certificates)
Preferred skills
Bare-metal automation, Low-level hardware expertise (routers, switches, BIOS, TPM), Advanced Kubernetes & CI/CD architecture
Technologies
Kubernetes, Terraform, Prometheus, Grafana, Datadog, Argo CD, Golang, Python, Linux, IPSec/VPN
Responsibilities
Own reliability and lifecycle of edge racks; Design and improve automation for provisioning edge fleet; Maintain secure network connecting edge to cloud; Participate in incident rotation and lead post-incident reviews; Define and monitor SLOs/SLIs/SLAs; Mentor fellow engineers; Act as top-level technical escalation point.
Seniority
Senior, hands-on IC
