Cloud Site Reliability Engineer

Role Overview

SambaNova is seeking a Cloud Site Reliability Engineer (SRE) to own reliability, performance, and scalability for its AI inferencing service. You will bridge software development and operations to ensure inference endpoints deliver high uptime, low-latency responses, and efficient resource utilization. The role includes participating in a shared on-call rotation for 24/7 service reliability.

What You’ll Do

• Service Ownership & On-Call

  • Take shared production ownership of the inferencing service, including:
    • availability, latency, performance, efficiency
    • change management, monitoring, emergency response, capacity planning
  • Support deployment of AI infrastructure in new regions (e.g., Asia, Europe, Latin America)
  • Participate in a balanced 24/7 on-call rotation (primary/secondary / follow-the-sun style)

• Operational Excellence & Incident Management

  • Lead incident response for issues impacting the inferencing service
  • Run blameless post-mortems and implement corrective actions
  • Emphasize prevention via automation, robust testing, and resilient system design
  • Maintain actionable alerts with low false-positive rates (avoid alert fatigue)

• Monitoring, Performance, and Scalability

  • Build and maintain advanced monitoring, alerting, and dashboards using tools such as:
    • Prometheus, Grafana, Datadog
  • Monitor service health and model performance (latency, throughput, error rates) and accelerator utilization
  • Identify performance bottlenecks and implement cost-effective auto-scaling for variable inference load

On-Call Principles

• Balanced rotation across the team to prevent disproportionate burden
• Prevention-focused approach (automation/system design)
• Actionable alerts requiring human intervention
• Blameless post-mortems and corrective action to prevent recurrence