Own end-to-end, state-motivated workflows for bare-metal server provisioning, independent hardware/firmware bundle rollouts and secure physical hardware decommissioning. Build end-to-end hardware and infrastructure observability pipelines and design high-signal, low-noise alerting and Service Level Objective (SLO) dashboards that drive sub-30-minute incident detection. Design and build seamless software integrations and abstraction layers between Google Cloud VMware Engine (GCVE) bare-metal infrastructure and Google's first-party hardware lifecycle, provisioning, repair, fleet management platforms.
Design and implement high-reliability recovery orchestration including one-click staggered rack/row power-up, automated thermal protection shutdowns, and deterministic host/cluster restoration. Apply Artificial Intelligence/Machine Learning (AI/ML) models, time-series anomaly detection, and agentic Root Cause Analysis (RCA) workflows over hardware telemetry, system logs, and crash dumps to predict imminent hardware failures.
Job description provided by Google.
View the original posting
