Staff Backend Engineer, ML Inference Systems

Build and operate backend infrastructure for large-scale ML inference powering billions of daily model-serving decisions. Drive the technical direction of low-latency, high-throughput serving systems, partnering with ML engineers to scale with growing model complexity. Improve production reliability using monitoring and observability (Prometheus, Grafana), and manage cloud infrastructure on GCP with Kubernetes. Promote strong backend engineering, testing, deployment, and DevOps/SRE best practices.