Software Engineer, Kernels/CUDA (C++)
xAI · Palo Alto, California; Seattle, Washington
What the posting says
Each fact carries its state:Statedfound in the postingConflictstwo statements disagree, both quotedNot mentionedthe posting does not say
Not mentioned in this posting
“Not mentioned” means the posting does not say. It is not a no. You could ask the recruiter.
- PayNot mentioned
- The posting does not say
- Employment typeNot mentioned
- The posting does not say
- Work arrangementNot mentioned
- The posting does not say
- ShiftNot mentioned
- The posting does not say
- ExperienceNot mentioned
- The posting does not say
- EducationNot mentioned
- The posting does not say
- Visa sponsorshipNot mentioned
- The posting does not say
Requirements, each with its sentence from the posting
These are the employer’s words. The index does not judge whether you meet them.
- No requirement has been itemised for this posting yet. The employer’s words are in the full posting below.
Read the full posting as the employer wrote it
SpaceX was founded under the belief that a future where humanity is out exploring the stars is fundamentally more exciting than one where we are not. Today, SpaceX is actively developing the technologies to make this possible, with the ultimate goal of making life multiplanetary and expanding consciousness to the stars.
SpaceXSI is building Super Intelligence to help humanity understand the universe. Our teams are building the full Super Intelligence stack: from our Colossus supercomputers, to Grok models, to our suite of applications, including Grok Bot, Grok Build, Grok Imagine, Grok Voice, and X. We're creating a powerful flywheel where more compute trains better models, better models power more useful products, and what we learn from people using those products shapes what we build next.
SOFTWARE ENGINEER, KERNELS/CUDA (C++)
We are building one of the world’s largest AI supercomputers from the ground up. As part of the Compute Infrastructure team, you will own both the raw GPU supercomputer and the platform layer that runs on top of it. You will work across the full stack — from low-level GPU kernel optimizations and Linux kernel internals to massive-scale orchestration and virtualization — to make training and inference at SpaceXSI as fast, reliable, and scalable as possible.
This is a broad, high-impact role that combines hardcore supercompute and compute infrastructure work. Your contributions will directly accelerate Grok’s training speed and overall AI progress.
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
BASIC QUALIFICATIONS:
- 1+ years of experience with low-level system programming in C/C++
PREFERRED SKILLS AND EXPERIENCE:
- Deep low-level systems programming (C/C++/PTX/SASS)
- Strong experience with large-scale GPU clusters or distributed compute infrastructure at production scale
- Hands-on work with GPU kernel optimization (CUTLASS, custom kernels, Nsight profiling)
- Track record of building or running high-performance infrastructure for AI workloads (training or inference platforms)
- Ability to reason from first principles and optimize for both memory-bound and compute-bound scenarios
COMPENSATION AND BENEFITS:
$150,000 - $280,000 USD
Base salary is just one part of our total rewards package at SpaceXSI, which also includes equity, comprehensive medical, vision, and dental coverage, access to a 401(k) retirement plan, short & long-term disability insurance, life insurance, and various other discounts and perks.
SpaceXSI is an equal opportunity employer. For details on data processing, view our Recruitment Privacy Notice.
The posting text is reproduced as the employer wrote it; the index adds nothing to it.