Senior Embedded Imaging Firmware Engineer — CUDA/Jetson

Urban-Sky; Denver (CO); On-site; USD 140,000 - 180,000; Full time

Benefits offered by this job

Stock options

Medical, Vision and Dental

Flexible PTO

Job summary

Urban Sky seeks a Senior Embedded Firmware Engineer to own the firmware, imaging pipeline, and data-movement stack behind EO/IR payloads—from sensor at the focal plane to the ground link. You will drive the CUDA image processing pipeline at the edge and architect high-rate data paths, balancing latency and onboard ML workloads.

The role emphasizes working with NVIDIA Jetson platforms, PCIe/CSI/USB interfaces, and camera integration, delivering clean, calibrated imagery for field events and

Qualifications

• 5+ years developing embedded firmware in C/C++ for embedded Linux and/or bare-metal/RTOS systems.
• Hands-on experience shipping on NVIDIA Jetson or comparable embedded Linux/SoC platforms.
• Deep experience moving high-rate data over PCIe (driver, DMA, endpoint/root-complex level).
• Experience building end-to-end camera/imaging systems, from sensor to downstream consumer.
• Working experience with image processing pipelines (debayering, calibration, correction) and CUDA or GPU-accelerated processing.
• Solid grounding in networking, data routing, and command-and-control infrastructure.
• Strong hardware debugging skills and comfort working from schematics.
• Experience with optical calibration and characterization - distortion modeling, vignetting/correction, MTF/sharpness measurement
• Familiarity with motion/temporal compensation techniques (registration, stabilization, temporal filtering) for imaging from moving platforms

Responsibilities

• Own embedded firmware for EO and IR payloads: sensor bring-up, driver development, and edge compute on NVIDIA Jetson platforms.
• Integrate cameras and sensors over PCIe, MIPI/CSI, and USB, and develop board-support packages for custom carrier boards, system-on-modules, and companion microcontrollers.
• Own the L0 image processing pipeline running in CUDA at the edge: debayering, white balance, gamma, and camera/lens correction.
• Own IR-specific processing: non-uniformity correction (NUC), bad-pixel replacement, and radiometric calibration.
• Develop multi-frame super-resolution and related computational imaging capabilities.
• Implement imagery metadata (KLV/MISB) so every frame carries accurate pointing, position, and time.
• Architect high-throughput data paths across the vehicle - PCIe as a first-class specialty - and the routing infrastructure that carries imagery, telemetry, and C2 across satellite, tactical-radio, and IP links.
• Optimize for latency, throughput, and determinism, and balance pipeline compute against onboard ML workloads sharing the same CUDA resources.
• Integrate payload firmware with the gimbal and motion-control stack, consuming pointing and autonomy commands from the broader payload software architecture.
• Develop and maintain optical calibrations for EO/IR payloads - lens distortion modeling, vignetting/flat-field correction, and MTF/sharpness characterization.
• Implement motion and temporal compensation (frame-to-frame registration, stabilization, and temporal filtering) to maximize effective image quality from a moving platform

Skills

Embedded firmware

C/C++

Embedded Linux

PCIe

CUDA

Networking

Hardware debugging

Tools

NVIDIA Jetson

Job description

Urban Sky seeks a Senior Embedded Firmware Engineer to own the firmware, imaging pipeline, and data-movement stack behind EO/IR payloads—from sensor at the focal plane to the ground link. You will drive the CUDA image processing pipeline at the edge and architect high-rate data paths, balancing latency and onboard ML workloads.

The role emphasizes working with NVIDIA Jetson platforms, PCIe/CSI/USB interfaces, and camera integration, delivering clean, calibrated imagery for field events and