Senior Principal Cloud Platform Engineer

About the role

The Cloud Platform team owns the production inferencing service that serves SambaNova's models to customers on RDU accelerators, including capacity planning, deployment, monitoring, and incident response across regions in the United States, Asia, Europe, and Latin America.

What you'll do

• Own the availability, latency, and efficiency of the production inferencing service,including change management, emergency response
• Define the reliability and platform engineering strategy for the service, including SLOs, error budgets, and multi-region architecture
• Build and maintain monitoring, alerting, and dashboards in Prometheus, Grafana, and Datadog covering service health, model latency and throughput, and RDU utilization
• Lead incident response for high-severity events, run blameless post-mortems, and drive systemic fixes and automation of the toil those incidents expose
• Find and fix performance bottlenecks, and design auto-scaling and capacity planning policies that handle variable inference load without overspending

What you need

• 10–18 yrs of experience
• Terraform
• CI/CD
• AWS
• Docker
• Kubernetes
• Linux
• Any graduate

Good to have

• Machine learning
• SQL
• NoSQL
• Redis
• Prometheus
• Grafana