Member of Technical Staff, Kernels

Magic

United States

Presencial

USD 225 000 - 550 000

Tempo integral

14 dias+

Uma candidatura completa num minuto

Currículo e carta de apresentação personalizados, prontos a enviar.

Ultrapassa os filtros ATS

Vantagens oferecidas por esta oferta de emprego

401(k) plan with 6% salary matching

Generous health, dental and vision insurance

Unlimited paid time off

Visa sponsorship and relocation stipend

Resumo da oferta

Magic is looking for a Kernel Engineer to design and maintain high-performance kernels for optimizing throughput and latency during training and inference. Candidates should have low-level programming experience targeting AI accelerators like NVIDIA Blackwell or Google TPUs. The role offers a competitive salary range from $225K to $550K, along with significant equity, comprehensive insurance, and unlimited paid time off. Join a small, focused team committed to building safe AGI.

Qualificações

Experience in developing and optimizing GPU kernels is required.
Depth in computer architecture and low-level optimizations preferred.
Ability to work effectively in a fast-paced team environment.

Responsabilidades

Design kernels to optimize throughput and latency.
Ownership of kernel design and production reliability.
Evaluate porting compute kernels to alternative hardware.

Conhecimentos

Low-level programming experience targeting AI accelerators

Develop and optimize GPU kernels

Strong expertise in computer architecture and low-level machine optimizations

Experience in kernel authoring frameworks

Agility and ownership mindset

Ferramentas

NCCL

MSCCLPP

Triton

Flash-Attention

Descrição da oferta de emprego

Magic’s mission is to build safe AGI that accelerates humanity’s progress on the world’s most important problems. We believe the most promising path to safe AGI lies in automating research and code generation to improve models and solve alignment more reliably than humans can alone. Our approach combines frontier-scale pre‑training, domain‑specific RL, ultra‑long context, and inference‑time compute to achieve this goal.

About The Role

As a Kernel Engineer, you will design, implement, and maintain high-performance kernels to optimize throughput and latency during training and inference. Magic’s long-context windows create distinct kernel optimization challenges around memory utilization, data movement, and sustained throughput.

What you’ll work on

Design and implement kernels that support high-performance long-context behavior
Ownership of kernel design, implementation, deployment, and production reliability
Focus on robustness, extensive testing, and functional correctness, while pushing on performance
Evaluate porting Magic’s compute kernels to alternative hardware options
Co-design kernels with understanding and interaction with training, inference, and RL teams
For a sample of our work, see Magic‑Attention, presented at GTC 2026

What we’re looking for

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

Compensation, Benefits And Perks (US)