22 Nov
|
Cerebras
|
Canada
Advance high-speed AI inference infrastructure at Cerebras Systems through latency optimization, reliability engineering, and production software.
As a Staff Engineer, you will help build the next-generation architecture of a globally distributed inference platform. The Inference Platform team runs orchestration across datacenter clusters and connects cloud components with machine learning services. Your work includes improving latency, throughput, capacity efficiency, and resilience under unpredictable demand. You will also guide senior engineers, make high-consequence decisions, and collaborate across adjacent systems. Cerebras serves leading model labs, global enterprises, and AI-native startups.
Key Responsibilities
Optimize latency, throughput, capacity efficiency,
and resilienceDevelop production software across testing and productionizationSet technical standards through design and code reviewsResolve production issues and cross-system bottlenecksTranslate requirements into scalable system designsRequirements:
Eight or more years of software engineering experienceExperience with large-scale distributed systems or cloud infrastructureBackground optimizing high-QPS system performanceStrong backend or systems programming in Go or C++Experience with ML inference or model serving preferredUse systems programming, performance optimization, and inference infrastructure experience to shape Cerebras Systems’ scalable AI platform.
📌 Staff Ai Inference Infrastructure Engineer (Canada)
🏢 Cerebras
📍 Canada