Kernel Engineer

About the role

Cerebras Systems is looking for a Kernel Engineer to develop high‑performance software that bridges hardware and software for cutting‑edge AI and HPC workloads. You will design, optimize, and scale deep‑learning kernels to fully exploit Cerebras’ custom, massively parallel processor architecture.

Key responsibilities

• Develop design specifications for new machine‑learning and linear‑algebra kernels and map them to the Cerebras WSE system using parallel programming algorithms.
• Write and debug highly optimized low‑level assembly and custom C‑like domain‑specific language routines targeting Cerebras hardware.
• Use mathematical models and performance analysis to guide design decisions.
• Integrate unit and system testing methodologies to verify kernel functionality and performance.
• Collaborate with chip and system architects to optimize instruction sets, microarchitecture, and I/O for next‑generation systems.

Required profile

• Bachelor’s, Master’s, PhD or equivalent in Computer Science, Computer Engineering, Mathematics or related fields.
• Strong understanding of hardware architecture concepts and ability to learn new hardware details.
• Excellent debugging skills for complex software stacks.

Required skills

• Proficiency in C++ and Python.
• Experience with low‑level assembly and custom C‑like (CSL) language development.
• Knowledge of parallel algorithms and distributed memory systems.
• Familiarity with accelerator programming on GPUs and FPGAs.
• Experience with machine‑learning frameworks such as TensorFlow and PyTorch.
• Understanding of HPC kernels and their optimization.

What we offer

• Opportunity to build a breakthrough AI platform beyond GPU constraints.
• Publish and open‑source cutting‑edge AI research.
• Work on one of the world’s fastest AI supercomputers.
• Job stability combined with startup vitality.
• Simple, non‑corporate work culture that respects individual beliefs.