Staff Site Reliability Engineer – Automation and Platform

📋 Description

• • Staff Site Reliability Engineer – Automation and Platform at Cerebras Systems Inc., leading the engineering effort to eliminate toil at scale by driving implementation of self-service delivery pipelines, shared observability, and common tooling for the world’s fastest AI inference service powered by the Wafer-Scale Engine (WSE).
• • Day-to-day responsibilities include defining and implementing a robust strategy for delivering and running software reliably across multiple datacenters and cloud-based solutions; architecting self-service platforms and internal tooling for product teams, external customers, and cluster operators; defining and evolving reliability practices for inference workloads including SLOs, SLIs, error budgets, blameless postmortems, chaos testing, and capacity forecasting; mentoring mid-level SREs, supporting critical incident escalations, and using production pain points to prioritize high-leverage automation work; measuring and driving impact through metrics such as toil reduction, deployment velocity, SLO compliance, MTTR, and adoption of self-service workflows.
• • Cerebras Systems builds the world’s largest AI chip, 56 times larger than GPUs, with a wafer-scale architecture that delivers industry-leading training and inference speeds. The company’s customers include top model labs, global enterprises, and cutting-edge AI-native startups, including a multi-year partnership with OpenAI to deploy 750 megawatts of scale for ultra high-speed inference. Cerebras Inference offers the fastest Generative AI inference solution in the world, over 10 times faster than GPU-based hyperscale cloud inference services.
• • In this role, you will learn to architect and deliver declarative GitOps-driven continuous delivery for model releases, capacity provisioning, and cluster upgrades; gain deep familiarity with a proprietary cloud control plane operating large-scale heterogeneous clusters; influence cross-functional stakeholders and lead complex projects end to end; mentor early-career SREs as platform engineers; and contribute to shifting reliability from an ops-only burden to a shared engineering discipline that underpins frontier AI inference at scale.