Principal SRE AI Inference
Posted 4
views
Summary
A principal-level Site Reliability Engineer who designs and runs the reliable infrastructure behind Cerebras's AI inference services across data centers and cloud. Day to day: defining SLOs and error budgets, building self-service platforms and automation, leading incident escalations, and mentoring senior SREs.
You will shape the architecture for reliable inference infrastructure across data centers and cloud environments. You will build self-service operational platforms, evolve SRE practices, lead incident escalations, mentor senior SREs, and measure improvements in reliability and operational efficiency.
Responsibilities
- Define and implement reliability strategy across data centers and cloud solutions
- Architect self-service platforms and internal tooling for critical workflows
- Define SLOs, SLIs, error budgets, postmortems, chaos testing, and capacity forecasting
- Mentor senior SREs and support critical incident escalations
- Prioritize automation based on production pain points
- Measure toil reduction, deployment velocity, SLO compliance, MTTR, and self-service adoption
Requirements
- 15+ years of SRE, infrastructure engineering, or platform engineering experience
- Experience with large-scale compute fleets, control planes, schedulers, orchestration systems, capacity management, and reliability automation
- Experience driving cross-team architecture for production control planes, fleet management, or self-service infrastructure
- Experience with observability, incident response, and SLO-based reliability management
- Ability to lead ambiguous technical programs and mentor senior engineers