SlipstreamJobs tracks this role from the company's public career site. Apply directly on the employer's site.
Salary: USD 156,000 - 186,000 / annual
Muon Space is seeking a GPU Software Engineer to join its High Performance Compute (HPC) team, designing and developing GPU-accelerated software for mission-critical workloads running onboard orbiting satellites. You will architect and implement GPU compute kernels (CUDA, OpenCL, HIP) for Earth-imaging sensor processing, RF signal analysis, and onboard AI/ML inference. The role spans the full development lifecycle: feasibility, concept, architecture, design, implementation, verification, lab qualification, and flight deployment.
Key responsibilities include designing and implementing GPU compute kernels for image processing, radio signal processing, and ML inference; architecting end-to-end GPU pipelines that ingest live sensor data and hand results to downlink or CPU subsystems; partnering with internal and external customers to transform algorithmic needs into efficient, flight-ready implementations under real-time and power constraints; profiling and optimizing GPU workloads to meet strict power budgets and real-time deadlines; owning verification and validation including unit tests, system-level tests, and hardware-in-the-loop testing; defining and evolving the GPU build and CI/CD environment with cross-compilation toolchains and containerized builds; collaborating with flight software, FPGA, payload, and system hardware engineers on interfaces and timing budgets; and translating mission requirements into robust designs and documentation.
Required qualifications include a Bachelor's or Master's degree in Computer Science, Computer Engineering, Electrical Engineering, Applied Math, or related field, plus 3+ years of professional experience developing GPU-accelerated software. You must have strong proficiency in C/C++ or Rust and Python, with deep familiarity with memory management, concurrency, and performance-oriented programming. Demonstrated production experience shipping GPU-accelerated software using CUDA, OpenCL, HIP, or similar is essential. Deep working knowledge of GPU architecture (SIMT execution, memory hierarchies, occupancy, kernel launch overhead) is required. You need proven experience developing and debugging on embedded Linux (Ubuntu on Nvidia Jetson/IGX platforms), including cross-compilation and device tree basics. Ability to write Linux userspace software integrating GPU compute with the rest of the system is critical. Strong communication skills and ability to work with customers are essential. Ability and willingness to obtain and maintain a U.S. security clearance is required (active clearance is a plus).
Nice-to-have skills include production experience with raw image or radio signal processing on GPUs, experience deploying ML inference on GPUs with quantization and model optimization, hands-on experience with DSP/RF workloads, experience with high-throughput data movement and RDMA, experience defining CI/CD for embedded software and hardware-in-the-loop automation, direct exposure to space or aerospace environments, and prior customer-facing or applied-engineering roles.
