Muon Space
GPU Software Specialist, Onboard Compute
$190K–$212K
San Jose, CA +1 · Full-time · Posted Aug 17, 2026
- Location
- San Jose, CA
San Jose, California, United States - Experience
- 3+ years of professional experience developing GPU-accelerated software.
- Education
- Bachelor's or Master’s degree in Computer Science, Computer Engineering, Electrical Engineering, Applied Math, or a related technical field.
- Visa sponsorship
- Must be a U.S. person, eligible to access the export-controlled information without export authorization, or eligible and reasonably likely to obtain the required export authorization. The company may decline to pursue export licensing for legitimate business reasons.
About the job
Design, optimize, verify, and deploy GPU-accelerated software for onboard satellite image and radio processing and AI/ML inference.
What you'll do
- Develop GPU kernels and end-to-end pipelines for sensor processing and ML inference under real-time and power constraints.
- Profile, optimize, verify, and validate GPU software, including hardware-in-the-loop testing.
- Own embedded GPU build and CI/CD environments and coordinate spacecraft interfaces with cross-functional teams.
What they ask for
- Bachelor's or Master's degree in a related technical field, plus 3+ years of professional GPU-accelerated software development.
- Strong proficiency in C/C++ or Rust, and Python; production experience shipping GPU software using CUDA, OpenCL, HIP, or similar.
- Deep knowledge of GPU architecture and demonstrated embedded Linux development, including cross-compilation.
- Ability and willingness to obtain and maintain a U.S. security clearance; must meet stated export-control access eligibility.
Nice to have
- Active security clearance.
- Experience with GPU image or radio processing, edge ML inference, DSP/RF, high-throughput data movement, embedded CI/CD, or mission-critical environments.
Pay
$190,000 - $212,000 USD base salary
Tools
C/C++, Rust, Python, CUDA, OpenCL, HIP, embedded Linux, Ubuntu
AI focus
Develop and optimize onboard GPU software for AI/ML inference, including adapting inference models for efficient on-orbit execution; edge deployment and model quantization are preferred experience.
Model-written summary · the original posting is authoritative