jobs

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 serv

In inglese

Company

Cerebras

Location

Sunnyvale, CA

Status

Open

Posted

2026-07-06T20:38:40.281+00:00

Cerebras is hiring a Principal SRE to build a reliability function for its wafer-scale AI inference service, used by frontier labs and enterprises. The work covers architecture for scaling the inference fleet: self-service delivery, observability, capacity orchestration, rollout safety and automation, plus SLOs and SLIs for latency, throughput and accuracy. It asks for 15+ years in SRE, platform or infrastructure engineering, experience with large compute fleets and control planes, and mentoring senior engineers. The role begins with two to three weeks of operational immersion, and no 24/7 on-call rotation.