GPU Software Specialist, Onboard Compute

Responsibilities

• Design and implement GPU compute kernels for onboard image processing, radio signal processing, and ML inference.
• Architect GPU pipelines that process live optical and radio sensor data and pass results to downlink or CPU decision-making subsystems.
• Port, adapt, and optimize customer code, models, and algorithms for real-time, power-constrained on-orbit execution.
• Profile and optimize GPU workloads, including occupancy, kernel launch configuration, and memory access patterns.
• Own unit, system-level, and hardware-in-the-loop verification and validation of GPU software.
• Define and operate the GPU build and CI/CD environment, including embedded-target cross-compilation toolchains and containerized builds.
• Collaborate with flight software, FPGA, payload, and hardware engineers on interfaces, data formats, and timing budgets.
• Translate mission and payload requirements into documented designs, trade studies, and interface specifications.
• Work with internal and external customers to guide algorithm and model adaptation for embedded GPU hardware.

Requirements

• Bachelor's or master's degree in Computer Science, Computer Engineering, Electrical Engineering, Applied Math, or a related technical field.
• At least three years of professional experience developing GPU-accelerated software.
• Strong proficiency in C/C++ or Rust and Python, including memory management, concurrency, and performance-oriented programming.
• Production experience shipping GPU-accelerated software with CUDA, OpenCL, HIP, or similar technologies.
• Deep knowledge of GPU architecture, SIMT execution, memory hierarchies, access patterns, occupancy, and kernel launch overhead.
• Experience developing and debugging on embedded Linux, including cross-compilation, device tree basics, and userspace/kernel driver interaction.
• Ability to write Linux userspace software integrating GPU compute through shared memory or similar mechanisms.
• Ability to work with customers to adapt algorithms and models for efficient execution on embedded GPU hardware.
• Strong written and verbal communication skills and ability to produce design documents, interface descriptions, and test reports.
• Ability and willingness to obtain and maintain a U.S. security clearance; active clearance is a plus.
• Experience with raw image or radio signal processing on GPUs is preferred.
• Experience deploying ML inference on GPUs, including quantization and edge model optimization, is preferred.
• Experience with DSP/RF workloads, Ethernet-based payload streams, RDMA, and zero-copy buffer techniques is preferred.
• Experience with embedded software CI/CD, containerization, and hardware-in-the-loop test automation is preferred.
• Space, aerospace, mission-critical software, customer-facing, or applied-engineering experience is preferred.

Benefits

• Hybrid work arrangement with three days per week on-site in the San Jose, California office.
• Medical, dental, and vision insurance.
• 401(k) retirement plan.
• Short- and long-term disability and life insurance.
• Three weeks of paid vacation for new employees.
• 12 paid holidays, unlimited sick time, and paid parental leave.
• Equity compensation is provided in addition to salary.