Staff SRE: AI Inference Platform Reliability Leader

Cerebras; San Carlos (CA); On-site; CAD 140,000 - 210,000; Full time

Job summary

Cerebras Systems is seeking a Staff SRE to lead the transformation of our reliability practices for AI inference at scale. The role focuses on building declarative, GitOps-driven CD for model releases and capacity provisioning, enabling self-service across multiple datacenters and cloud-based solutions.

You will mentor the SRE sub-team, reduce toil, and collaborate with product teams, customers, and cluster stakeholders.

Qualifications

• 8+ years in SRE, infrastructure engineering, or platform engineering in demanding environments.
• Deep expertise operating large scale clusters with a proprietary cloud control plane.
• Proven track record delivering CI/CD or GitOps systems with strong observability.

Responsibilities

• Define and implement a robust strategy for delivering and running software reliably at scale across multiple datacenters and cloud solutions.
• Architect self-service platforms and tooling for product teams, customers, and cluster operators.
• Define and evolve reliability practices for inference workloads, including SLOs/SLIs and capacity forecasting.
• Mentor mid-level SREs and prioritize automation work based on production pain points.
• Measure impact through toil reduction, deployment velocity, and SLO adherence.

Skills

SRE

Infrastructure

GitOps

CI/CD

Observability

Automation

Distributed systems

Tools

Argo CD

Prometheus

Loki

Tempo

Mimir

Job description

Cerebras Systems is seeking a Staff SRE to lead the transformation of our reliability practices for AI inference at scale. The role focuses on building declarative, GitOps-driven CD for model releases and capacity provisioning, enabling self-service across multiple datacenters and cloud-based solutions.

You will mentor the SRE sub-team, reduce toil, and collaborate with product teams, customers, and cluster stakeholders.