Principal SRE - AI Inference

Cerebras Systems builds the world's largest AI chip, 56 times larger than GPUs. This architecture allows Cerebras to deliver industry-leading training and inference speeds; over 10 times faster than GPU-based hyperscale cloud inference services. This order of magnitude increase in speed is transforming the user experience of AI applications, unlocking real-time iteration and increasing intelligence via additional agentic computation. Cerebras works with the leading model labs, global enterprises, and cutting-edge AI-native startups. OpenAI recently announced a multi-year partnership https://openai.com/index/cerebras-partnership/ with Cerebras, to deploy 750 megawatts of scale, transforming key workloads with ultra high-speed inference. About the Role We are building a high-performance SRE function to support one of the world’s fastest-growing AI inference services, powered by the Wafer-Scale Engine (WSE). This team will help deliver world-class, ultra-reliable inference infrastructure for leading model builders such as OpenAI and other frontier labs. As a Principal SRE, you will define and drive the technical architecture for scaling our inference fleet through self-service delivery, shared observability, capacity orchestration, rollout safety, and operational automation. This role starts with 2–3 weeks of hands-on operational immersion to build deep context on the current stack, production pain points, and high-stakes workflows. From there, your mandate shifts to architecting the “tomorrow” layer: a unified capacity management and production control plane that enables reliable capacity planning, workload placement, rollout safety, validation, and operational decision-making across large-scale inference infrastructure. Success in the first year means core engineering teams, product managers, external customers, and cluster stakeholders can execute critical operational workflows through self-service systems with strong guardrails, clear ownership, and minimal depende

Department: Software; Team: Cloud