Staff Software Engineer, GPU Inference

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 8+ years of experience, strong C++ and Python skills, and expertise in high-performance model-serving frameworks and GPU execution.

Location: Toronto, CAN; Sunnyvale, CA
Employment: full time
Work pattern: unspecified
Seniority: senior

APPLY ON THE EMPLOYER’S SITE ↗

Source and currency

This vacancy came from the organization’s official Ashby feed. Source update: 2026-10-21T15:47:18.233+00:00. Check the employer’s page for the complete description, current availability and application terms.

• jobs.ashbyhq.com/cerebras/b418fbca-9a33-4ac5-adb3-24dd57b1c678 ↗

Cerebras RESEARCH PROFILE ↗