Global AI MapJOBS / Cerebras
Software Engineer, GPU Inference
Sunnyvale, CA; Toronto, CAN
Role
The role involves productionizing and optimizing a GPU inference stack for Cerebras's disaggregated AI systems, focusing on reliability and performance. Candidates must have 5+ years of experience in C++ and Python, with expertise in production inference systems and GPU performance optimization.
Location: Sunnyvale, CA; Toronto, CAN
Employment: full time
Work pattern: unspecified
Seniority: mid
APPLY ON THE EMPLOYER’S SITE ↗
Source and currency
This vacancy came from the organization’s official Ashby feed. Source update: 2025-11-25T18:10:40.280+00:00. Check the employer’s page for the complete description, current availability and application terms.