Kernel Engineer (AI)

Location: San Francisco, on-site; relocation support to San Francisco may be available.

Salary: $225,000–$550,000 annually, plus significant equity.

Company

hirify.global develops safe AGI through frontier-scale pre-training, domain-specific reinforcement learning, long-context models, and inference-time compute.

What you will do

• Design, implement, deploy, and maintain high-performance kernels for long-context model training and inference.
• Optimize memory utilization, data movement, latency, and sustained throughput.
• Own kernel reliability, robustness, extensive testing, and functional correctness in production.
• Evaluate porting compute kernels to alternative hardware platforms.
• Co-design kernels with 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, or Flash-Attention.
• Deep expertise in computer architecture, low-level machine optimization, and code generation.
• Broad understanding of machine learning and the ability to work across training, inference, and reinforcement learning.
• Agility, ownership mindset, grit, and a strong focus on quality.

Nice to have

• Experience with Mosaic, Pallas, GPU, TPU, or Mojo kernel authoring frameworks.

Culture & Benefits

• Small, fast-paced, highly focused team.
• Equity as a significant part of total compensation.
• 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 may be available.