Member of Technical Staff, Kernels

Highlights

• Optimize throughput and latency for ultra-long-context training and inference.
• Own kernels end-to-end from design through deployment and production reliability.
• Co-design kernels with training, inference, and RL teams to advance safe AGI.

What they offer

• Equity is a significant part of total compensation, in addition to salary
• 401(k) plan with 6% salary matching
• Generous health, dental and vision insurance for you and your dependents
• Unlimited paid time off
• Visa sponsorship and relocation stipend to bring you to SF, if possible

Ideal candidate

Deep systems thinker with grit and ownership mindset who loves low-level optimization and robust engineering. Excited to push performance for long-context AGI in a small, fast-paced, mission-driven team.

Requirements

• Low-level programming experience targeting AI accelerators such as NVIDIA Blackwell or Google TPUs
• Develop and optimize GPU kernels in frameworks such as NCCL, MSCCLPP, CUTLASS, CuTeDSL, Triton, Quack, Flash-Attention, and similar frameworks
• Experience in other kernel authoring frameworks such as Pallas/Mosaic (GPU or TPU), or Mojo also maps well to the work on Magic's kernel team
• Strong depth over shallow breadth: for kernel engineering, we prefer candidates with deep expertise in computer architecture, low-level machine optimizations, and code generation, with breadth across ML
• Agility, ownership mindset, and grit