Kernel Engineering Manager

About the role:

MAX is Modular's inference tech stack, built to run GenAI models fast across NVIDIA, AMD, Qualcomm, Trainium, TPU and more. The MAX Kernel team is the performance foundation of that stack, developing kernels using Mojo, GEMM, attention (MHA/MLA/MSA), MoE routing and grouped matmul, and the portable tile abstractions that let one kernel lower to many targets.

As the Engineering Manager of the MAX Kernel team, you will lead a team of kernel engineers, own the kernel roadmap and the per-model × per-hardware performance optimization to the best vendor and open-source stacks. You will partner closely with the Framework, Serve, Compiler/Runtime and Hardware Enablement teams, and help grow a kernel engineering community that spans Modular and Qualcomm.

LOCATION: Candidates based in the United States are welcome to apply. You can work in our office in Los Altos, CA or remotely from home. Onboarding for new hires is conducted in-person in our Los Altos, CA office.

What you will do:

• Lead, hire, coach and grow a team of ~12 kernel engineers across NVIDIA, AMD and ASIC hardwares; own career development, performance management and team health. • Own the MAX kernel roadmap and delivery: match or beat the performance of other open-source kernel libraries on each business essential model × hardware target. • Support portable kernel architecture (TileTensor / TensorEngine / TileIO, reusable building blocks such as MegaFFN and the attention family) together with tech…