Senior GPU Kernel/CUDA Engineer (C++) - Equity & AI Infra

X AI; Palo Alto (CA); On-site; USD 220,000 - 357,000; Full time

Benefits offered by this job

Equity

Medical coverage

Vision coverage

Dental coverage

401(k)

Job summary

SpaceXSI, based in Palo Alto, CA, is hiring a Sr. Software Engineer, Kernels/CUDA (C++) to own the GPU supercomputer and platform layer.

You will work across low-level kernel internals to large-scale orchestration, accelerating Grok's training and inference pipelines at scale. The role combines hardcore systems programming with performance-focused infrastructure, collaborating with AI research teams to deliver production-ready, scalable solutions.

Qualifications

• 5+ years of experience with low-level system programming in C/C++.
• Experience with GPU kernel optimization and distributed compute infrastructure.

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

C/C++

PTX/SASS

GPU kernel optimization

Nsight profiling

Distributed compute infra

Tools

CUTLASS

Nsight

CUDA

Tensor Cores

Job description

SpaceXSI, based in Palo Alto, CA, is hiring a Sr. Software Engineer, Kernels/CUDA (C++) to own the GPU supercomputer and platform layer.

You will work across low-level kernel internals to large-scale orchestration, accelerating Grok's training and inference pipelines at scale. The role combines hardcore systems programming with performance-focused infrastructure, collaborating with AI research teams to deliver production-ready, scalable solutions.