Cerebras
Kernel Engineer
United States and Canada · Full-time · Posted Feb 23, 2026
- Education
- Bachelor’s, Master’s, PhD or foreign equivalents in Computer Science, Computer Engineering, Mathematics, or related fields.
About the job
Develop and optimize machine-learning and HPC kernels for Cerebras hardware, improving performance and validating kernel libraries.
What you'll do
- Design and implement parallel machine-learning and linear algebra kernels for the Cerebras WSE System.
- Optimize and debug kernel routines in low-level assembly and CSL, using performance analysis to guide design.
- Develop testing methods and collaborate with chip and system architects on future systems.
What they ask for
- Bachelor’s, Master’s, PhD or foreign equivalents in Computer Science, Computer Engineering, Mathematics, or a related field.
- Understanding of hardware architecture concepts and willingness to learn a new architecture.
- Proficiency in C++ and Python.
- Knowledge of library or API development best practices, plus strong debugging skills.
Nice to have
- Kernel development or testing experience; familiarity with parallel algorithms and distributed memory systems.
- Accelerator programming experience, or familiarity with neural networks and frameworks such as TensorFlow and PyTorch, or HPC kernel optimization.
Tools
C++, Python, Cerebras WSE System, CSL, TensorFlow, PyTorch
AI focus
Develop and optimize machine-learning kernels and algorithms for AI workloads on Cerebras hardware.
Model-written summary · the original posting is authoritative