over 2 years ago
Base Salary
$225k - $550k/yr
Responsibilities
- Design and implement kernels supporting high-performance long-context behavior.
- Own kernel design, implementation, deployment, and production reliability.
- Prioritize robustness, extensive testing, functional correctness, and performance optimization.
- Evaluate porting compute kernels to alternative hardware options.
- Co-design kernels with the training, inference, and reinforcement learning teams.
Requirements
- Low-level programming experience targeting AI accelerators such as NVIDIA Blackwell or Google TPUs.
- Experience developing and optimizing GPU kernels with frameworks such as NCCL, MSCCLPP, CUTLASS, CuTeDSL, Triton, Quack, and Flash-Attention.
- Experience with kernel authoring frameworks such as Pallas, Mosaic, or Mojo is also relevant.
- Deep expertise in computer architecture, low-level machine optimizations, and code generation, with breadth across machine learning.
- Agility, an ownership mindset, and grit.
Benefits
- Annual salary range of $225K-$550K based on experience, plus significant equity.
- 401(k) plan with 6% salary matching.
- Health, dental, and vision insurance for employees and dependents.
- Unlimited paid time off.
- Visa sponsorship and relocation stipend to San Francisco, if possible.
- Small, fast-paced, highly focused team.
Categories
About Magic
Magic is working on frontier-scale code models to build a coworker, not just a copilot. Come join us: http://magic.dev