Space GPU Software Engineer – Onboard AI & Imaging

Muonspace; San Jose (CA); Hybrid; USD 156,000 - 186,000; Full time

Benefits offered by this job

Equity

Medical, dental and vision insurance

401(k) retirement plan

Paid vacation and holidays

Paid parental leave

Job summary

Muon Space seeks a GPU Engineer for the HPC team to design and develop GPU-accelerated software for onboard satellite compute. You will build kernels and pipelines for Earth-imaging and ML inference, collaborating with FPGA, flight software, and payload teams.

You will optimize performance under strict power and real-time constraints, participate in verification and CI/CD, and help translate mission requirements into robust flight-ready software.

Qualifications

• Bachelor’s or Master’s degree in a related field, plus 3+ years of GPU-accelerated software experience.
• Proficient in C/C++ or Rust and Python, with memory management and concurrency knowledge.
• Experience shipping GPU-accelerated software using CUDA, OpenCL, HIP, or equivalents.
• Deep knowledge of GPU architecture, SIMT, memory hierarchies and occupancy.
• Experience developing on embedded Linux with cross-compilation and device-tree basics.
• Ability to write Linux userspace software that integrates GPU compute with other subsystems.
• Ability to work with customers to adapt workloads to embedded GPUs under real-time constraints.

Responsibilities

• Design and implement GPU compute kernels (CUDA) for onboard processing and ML workloads.
• Architect end-to-end GPU pipelines ingesting live sensor data and produce actionable results.
• Port and optimize workloads for on-orbit execution within power constraints.
• Profile and tune GPU workloads to meet real-time deadlines and power budgets.
• Own verification, unit tests, and hardware-in-the-loop testing for GPU software.

Skills

CUDA

C/C++

Python

GPU architecture

Embedded Linux

Cross-compilation

CI/CD

Verbal/written communication

Education

Bachelor's or Master’s degree in CS/EE/Applied Math

Tools

CUDA/OpenCL/HIP

Job description

Muon Space seeks a GPU Engineer for the HPC team to design and develop GPU-accelerated software for onboard satellite compute. You will build kernels and pipelines for Earth-imaging and ML inference, collaborating with FPGA, flight software, and payload teams.

You will optimize performance under strict power and real-time constraints, participate in verification and CI/CD, and help translate mission requirements into robust flight-ready software.