Staff GPU Inference SDET
Cerebras · Sunnyvale, CA · Toronto, CAN
CHECKED 7H AGO
Infrastructureremotestaff
At a glance
Highlights
- Founding quality and reliability lead for a new GPU inference team.
- Build end-to-end qualification for rack-scale accelerated compute fleets.
- Deliver ultra-high-speed inference enabling real-time AI iteration.
Ideal candidate
Systems-minded quality leader who thrives owning reliability end-to-end for large-scale AI infrastructure and turning complex failures into automated gates. You care deeply about performance stability and production-grade resilience.
Requirements
- 8+ years as an SDET, Infrastructure Quality Lead, or Systems Test Engineer
- Hands-on bring-up, provisioning and validation of multi-node GPU clusters in cloud or data center environments
- Deep understanding of LLM serving engines including prefill vs decode disaggregation, KV-cache and dynamic batching
- Expert-level Python for custom test automation frameworks, diagnostic tooling and CI/CD integration
- Strong proficiency with Kubernetes, Slurm, Ray and high-performance interconnects like InfiniBand, RoCE, NCCL
- Proven root-cause analysis across software/hardware boundaries, stress testing and failure simulation
Lab profile
About Cerebras
Builds wafer-scale AI chips and cloud systems for ultra-fast training and inference.
What they build
- Wafer-scale AI chips
- AI training systems
- Cloud inference service
Known for
- 56x larger chips than GPUs
- 10x faster inference than GPU clouds
- Industry-leading training speed