Senior CUDA Kernel Engineer (Equity Eligible)

SpaceX Super Intelligence; Palo Alto (CA); On-site; USD 220,000 - 357,000; Full time

Benefits offered by this job

Equity

Medical, Vision, and Dental coverage

401(k) retirement plan

Disability insurance

Life insurance

Discounts and perks

Job summary

SpaceXSI is building one of the world’s largest AI supercomputers and a full stack for Grok models. This Sr. Software Engineer will own GPU kernels and platform layers, optimizing CUDA work and distributed infrastructure across massive clusters.

You will collaborate with AI research to deliver scalable, production-grade performance for training and inference, impacting Grok’s capabilities and SpaceXSI’s roadmap.

Qualifications

• 5+ years of experience with low-level system programming in C/C++.
• Experience with GPU clusters or distributed compute at production scale.
• Proven ability to optimize GPU kernels and memory hierarchy.

Responsibilities

• Design, build, and optimize massive GPU clusters for extreme-scale training and inference workloads.
• Develop and tune low-level CUDA kernels (GeMM, Attention, etc.), using CUTLASS, Tensor Cores, and Nsight for maximum performance
• Profile, debug, and eliminate bottlenecks across GPU memory hierarchy, networking fabric, filesystems, and multi-GPU operation
• Collaborate closely with AI research teams to deliver production-grade performance and scalability

Skills

Low-level C/C++

CUDA kernels

Nsight profiling

Distributed compute

GPU performance

Tools

CUTLASS

Tensor Cores

Nsight

Job description

SpaceXSI is building one of the world’s largest AI supercomputers and a full stack for Grok models. This Sr. Software Engineer will own GPU kernels and platform layers, optimizing CUDA work and distributed infrastructure across massive clusters.

You will collaborate with AI research to deliver scalable, production-grade performance for training and inference, impacting Grok’s capabilities and SpaceXSI’s roadmap.