Site Reliability Engineer

About the company

• Cerebras Systems builds the world's largest AI chip, powering ultra-reliable AI inference services for leading model builders such as OpenAI.

Responsibilities

• Define and implement strategy for delivering and running software reliably at scale across multiple datacenters and cloud solutions.
• Architect self-service platforms and internal tooling for safe workflow triggering and observation.
• Define reliability practices for inference workloads: SLOs/SLIs for latency, throughput, accuracy; error budgets; blameless postmortems; chaos testing; capacity forecasting.
• Mentor mid-level SREs, support critical incident escalations, prioritize automation work.
• Measure impact via toil reduction, deployment velocity, SLO compliance, MTTR, self-service adoption.

Requirements

• 8+ years in SRE, infrastructure, or platform engineering at large scale (FAANG, hyperscaler).
• Deep expertise operating large-scale heterogeneous clusters with proprietary cloud control plane.
• Proven track record designing CI/CD or GitOps systems using Argo CD or similar.
• Hands-on experience with observability systems: Loki, Tempo, Mimir, Prometheus.
• Ability to lead complex projects end to end and influence cross-functional stakeholders.

Nice-to-haves

• Experience with Bazel or other large-scale build systems.
• Background in AI/ML inference systems, model serving runtimes, GPU orchestration, drift monitoring.
• Prior work on predictive autoscaling, chaos engineering, cost-aware capacity planning.

Conditions

• Location: SF Bay Area or Toronto.
• No 24/7 on-call rotations.