Cerebras
Software Engineer, Kernel Reliability
United States and Canada · Full-time · Posted Sep 15, 2026
- Experience
- No specific years required; new college graduates are welcome. Required skills may be demonstrated through projects, internships, or coursework.
About the job
Improves the reliability and debuggability of Cerebras compute clusters, software services, and kernel-focused systems through engineering, failure analysis, and cross-team collaboration.
What you'll do
- Build tools and provide debugging support to reduce downtime and speed up failure analysis.
- Improve kernel and software-stack reliability, and contribute to reliability-focused architecture design.
- Participate in incident response, root-cause analysis, and post-mortems; drive reliability improvements.
What they ask for
- Strong programming skills in C/C++ and Python.
- Foundations in operating systems, computer architecture, and systems programming.
- Ability to debug complex issues using logs, traces, and standard debugging workflows; interest in root-cause analysis.
Nice to have
- Exposure to parallel and distributed programming.
- Experience with debug or diagnostic tools, or familiarity with debugging distributed and parallel applications.
Tools
C/C++, Python
AI focus
The role supports reliability of inference and training systems and internal production services; it does not specify developing AI models or AI methods.
Model-written summary · the original posting is authoritative