Sr. Software Engineer, Kernels/CUDA (C++)

SpaceXSI•Palo Alto, CA

10h•$220,000 - $357,000

About The Position

SpaceXSI is building Super Intelligence to help humanity understand the universe, including the compute infrastructure, models, and applications that make up its Super Intelligence stack. The Compute Infrastructure team is building a large AI supercomputer and its platform layer. In this role, you will work across low-level GPU kernel optimization, Linux kernel internals, orchestration, and virtualization to improve the speed, reliability, and scalability of AI training and inference. Your work will contribute directly to Grok’s training speed and overall AI progress.

Requirements

At least 5 years of experience with low-level system programming in C/C++.

Nice To Haves

Deep low-level systems programming experience in C/C++/PTX/SASS.
Strong experience with large-scale GPU clusters or distributed compute infrastructure at production scale.
Hands-on experience optimizing GPU kernels using CUTLASS, custom kernels, and Nsight profiling.
A track record of building or operating high-performance infrastructure for AI workloads, including training or inference platforms.
Ability to reason from first principles and optimize for memory-bound and compute-bound scenarios.

Responsibilities

Design, build, and optimize massive GPU clusters for extreme-scale training and inference workloads.
Develop and tune low-level CUDA kernels, including GeMM and Attention, using CUTLASS, Tensor Cores, and Nsight.
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.