Description
Cerebras Systems is hiring an on-field Kernel Reliability Software Engineer to improve the reliability of its advanced compute clusters and inference, training, and production services. The role focuses on kernel-centric reliability, failure analysis, incident response, root-cause analysis, debugging tools, and collaboration with systems, software, ASIC, and hardware architecture teams. Candidates should have strong C/C++ and Python skills, systems programming fundamentals, and experience or coursework in debugging complex issues; parallel, distributed, and computer architecture experience are preferred. New college graduates are welcome.
