Senior GPU Kernel/CUDA Engineer for Exascale AI Infra

xAI; Palo Alto, Seattle (CA, WA); On-site; USD 200,000 - 375,000; Full time

Job summary

SpaceXSI is building one of the world’s largest AI supercomputers, and the Compute Infrastructure team will own the raw GPU cluster and the platform layer that runs on top of it. You will work across the full stack—from low-level GPU kernel optimizations to large-scale orchestration—to speed up Grok’s training and AI progress.

The role combines hardcore supercompute with compute infrastructure, offering high impact, collaboration with AI researchers, and a path to optimize for both memory-bound

Qualifications

• 5+ years of experience with low-level system programming in C/C++.
• Experience with Linux kernel internals and GPU compute infrastructure.
• Proven ability to optimize memory-bound and compute-bound workloads.

Responsibilities

• Design, build, and optimize massive GPU clusters for extreme-scale training and inference workloads.
• Develop and tune low-level CUDA kernels (GeMM, Attention) using CUTLASS, Tensor Cores, and Nsight for maximum performance.
• Profile, debug, and eliminate bottlenecks across GPU memory hierarchy, networking, 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

PTX/SASS

GPU kernel optimization

Distributed compute

Nsight profiling

System programming

Tools

CUTLASS

Nsight

Tensor Cores

GeMM

Job description

SpaceXSI is building one of the world’s largest AI supercomputers, and the Compute Infrastructure team will own the raw GPU cluster and the platform layer that runs on top of it. You will work across the full stack—from low-level GPU kernel optimizations to large-scale orchestration—to speed up Grok’s training and AI progress.

The role combines hardcore supercompute with compute infrastructure, offering high impact, collaboration with AI researchers, and a path to optimize for both memory-bound