Develop and optimize foundational ML and linear algebra kernels in assembly and CSL for the Cerebras WSE System.
Originally posted 5 February 2026 by the employer.
About the role
As a Kernel Engineer, you will develop high-performance software solutions for AI and HPC workloads, implementing, optimizing, and scaling deep learning operations on custom, massively parallel processor architecture. Your focus will be on designing, performance tuning, and validating foundational ML and HPC kernels mapped to the Cerebras WSE System.
What you'll do
- Develop design specifications for machine learning and linear algebra kernels, mapping them to the Cerebras WSE System using parallel programming algorithms.
- Develop and debug kernel routines using low-level assembly instructions and a custom C-like domain-specific language (CSL) targeting the Cerebras hardware system.
- Use mathematical models and analysis to measure software performance and inform design decisions.
- Develop and integrate unit and system testing methodologies to verify the functionality and performance of kernel libraries.
- Study emerging trends in machine learning applications to evolve kernel library architecture for neural networks.
- Interact with chip and system architects to optimize instruction sets, microarchitecture, and IO.
What you'll need
- Bachelor’s, Master’s, PhD or foreign equivalent in Computer Science, Computer Engineering, Mathematics, or a related field.
- Understanding of hardware architecture concepts and comfort with learning the details of a new hardware architecture.
- Proficiency in C++ and Python programming languages.
- Knowledge of library and/or API development best practices.
- Strong debugging skills across complex software stacks.
Nice to have
- Experience in kernel development and/or testing.
- Familiarity with parallel algorithms and distributed memory systems.
- Experience programming accelerators such as GPUs and FPGAs.
- Familiarity with machine learning neural networks and frameworks such as TensorFlow and PyTorch.
- Familiarity with HPC kernels and their optimization.
More semiconductor jobs: Cerebras jobs · Embedded software jobs · Sunnyvale jobs
This role has been open 102 days — well above the 64-day median for Systems Software Engineering roles.
Systems Software Engineering · Systems Software
|
Open roles in category
686
|
Median days open
64 d
|
Category median salary (all employers)
$219k
|
See the full market breakdown ▾Category comparison, and who else is hiring
| Metric | Cerebras | All employers we track in this specialty (686 roles · 73 employers) |
|---|---|---|
| Open roles in this specialty | 13 | 686 |
| Open roles in the wider Software, Firmware & Systems family | 70 | 6475 · 156 employers |
| Median days open | 102 d | 64 d (+38 d vs this employer) |
| Median salary (USD postings) | — | $219k |
Who's hiring in this category
- NVIDIA · 161 open roles · median 52 d
- Qualcomm · 157 open roles · median 86 d
- AMD · 63 open roles · median 57 d
- Arm Holdings · 31 open roles · median 9 d
- Mobileye · 27 open roles · median 92 d
- Broadcom · 15 open roles · median 72 d
How we counted: 686 open Systems Software Engineering (Systems Software) roles from 73 employers tracked in the SemiconductorJobs index, counted 6 Nov 2026. Specialty figures count only roles carrying this exact specialty label, so an employer's related work in neighbouring specialties is not included there — it is counted in the wider Software, Firmware & Systems family row. Figures refresh nightly.