Sr. Software Engineer, Kernels/CUDA (C++)
Design, build, and optimize massive GPU clusters for extreme-scale training and inference workloads; develop and tune low-level CUDA kernels; 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.
- Palo Alto, California, United States
- Full-time
- $220K–$357K per year
- Posted Nov 6, 2026
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
Requirements
Nice to have: Deep low-level systems programming, Strong experience with large-scale GPU clusters or distributed compute infrastructure at production scale, Hands-on work with GPU kernel optimization, Track record of building or running high-performance infrastructure for AI workloads, Ability to reason from first principles and optimize for both memory-bound and compute-bound scenarios
Skills
Benefits
- equity
- comprehensive medical
- vision
- dental coverage
- 401(k) retirement plan
- short & long-term disability insurance
- life insurance
- discounts and perks
More jobs nearby
Full description
SpaceXAISign up for a free job alert to see SpaceXAI's profile, website and LinkedIn, and the same for every employer on Referso Jobs.