Kernel Software Manager

About the role

Cerebras Systems is looking for a Kernel Software Manager to lead the development of high‑performance software that bridges hardware and AI workloads. You will guide a team that designs, optimizes, and validates machine‑learning and HPC kernels for our custom wafer‑scale engine.

Key responsibilities

• Define design specifications for new ML and linear‑algebra kernels and map them to the Cerebras WSE system.
• Develop and debug low‑level assembly and custom C‑like (CSL) routines that implement parallel algorithms on the hardware.
• Measure performance with mathematical models, guide design decisions, and integrate unit and system tests.
• Monitor emerging ML trends and evolve the kernel library to support state‑of‑the‑art neural networks.
• Collaborate with chip and system architects to optimize instruction sets, micro‑architecture, and I/O for next‑generation systems.

Required profile

• Bachelor’s, Master’s or PhD in Computer Science, Computer Engineering, Mathematics or a related field.
• Proven experience leading technical teams, mentoring engineers and driving execution.
• Strong understanding of hardware architecture concepts and willingness to dive into new system designs.

Required skills

• C++ programming.
• Python scripting.
• Low‑level assembly language development.
• Custom C‑like (CSL) language for kernel implementation.
• Parallel programming and distributed memory algorithms.
• Performance optimization and debugging of complex software stacks.

What we offer

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