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

Job description

We see the potential inside everything and everyone. Starting with you. Orbem uses AI to industrialize MRI, delivering non-invasive insight into everything from fruits to eggs to the human body. We are transforming what is becoming the world's largest biological dataset into actionable intelligence to reduce waste, increase quality, and accelerate the shift toward a more sustainable and healthier future. Headquartered and founded in Munich, Germany, with an office now in Houston, Texas, our world-class team is scaling inside-out technology to transform how humanity sees and understands biological matter. Help us see what's possible. Join us. Your Role Orbem’s AI-powered MRI systems run on edge infrastructure deployed directly at customer sites, such as hatcheries and food processing plants. As an Expert Site Reliability Engineer, you will own the reliability, availability, and performance of this growing global fleet. You are the team’s deepest technical authority on the on-premise platform, setting architecture and standards through hands-on expertise. You will own the hardware, network, operating system, and Kubernetes layers that power teams like Data, Machine Learning, and Software. Your Day-to-Day As an Individual Contributor on the expert track, your responsibilities center entirely on deep technical ownership and execution: Edge Infrastructure Ownership Own the reliability and lifecycle of our edge racks: server hardware, network equipment, custom Linux-based OS, and the GPU-enabled Kubernetes layer running our AI classification services. Design and improve automation for provisioning our growing fleet (50+ edge clusters and counting) using tools like Terraform, BMC/IPMI, and router APIs. Maintain the secure network connecting edge deployments to our central cloud, and the tooling that enables safe software delivery to the fleet. Reliability & Incident Management Participate in the rotation of support on weekdays and own triage and resolution for escalated production issues. Lead post-incident reviews and turn findings into lasting, automated fixes. Define and monitor SLOs/SLIs/SLAs for physical edge systems running unattended in the field. Extend our observability stack (Prometheus, custom hardware exporters, Grafana, Datadog) to catch issues proactively, often before customers notice. Architecture, Collaboration & Craft Set technical direction for…