Software Engineer I, Perception

Responsibilities

• Implement Extended Kalman Filters, Hungarian data association, and track-management logic for multi-object tracking.
• Train neural networks for object detection, classification, threat discrimination, and re-identification using models such as YOLO and ResNet.
• Build hybrid perception pipelines combining neural detections, classical tracking, coordinate transformations, and angle-only navigation measurements.
• Develop image-processing chains including hot-pixel filtering, adaptive thresholding, centroiding, connected-component analysis, and star-catalog matching.
• Quantize and deploy neural networks to edge hardware using C++ inference engines and optimize them for space-qualified processors.
• Implement transformations from pixel coordinates through camera and body frames to ECI while accounting for lens distortion and attitude uncertainty.
• Generate synthetic spacecraft imagery and labeled datasets using Blender and domain randomization.
• Validate end-to-end performance through software-, processor-, and hardware-in-the-loop testing with real camera feeds.

Requirements

• Currently pursuing or recently completed a bachelor's or master's degree in computer science, electrical engineering, robotics, aerospace engineering, or a related technical field.
• Coursework in computer vision and estimation theory, or willingness to learn both.
• Proficiency in Python and some exposure to C++.
• Familiarity with either classical tracking and data association or deep learning and neural-network training.
• Understanding of linear algebra, probability, and coordinate transformations.
• Ability to read and implement research from robotics and machine-learning venues such as ICRA, IROS, CVPR, and NeurIPS.
• Strong debugging skills involving lost tracks, numerical instability, and model failure modes.
• U.S. citizenship or other qualifying authorization required for ITAR and facility-access requirements.
• Preferred experience includes Extended Kalman Filters, multi-object tracking, state estimation, PyTorch or TensorFlow, YOLO, Faster R-CNN, coordinate frames, ONNX, TensorRT, OpenCV, Blender or Unreal, data-association algorithms, embedded deployment, ROS, and multimodal sensor fusion.

Benefits

• Three-month temporary employment engagement with potential conversion to regular employment based on performance and business need.
• Onsite work near Centennial, Colorado or Long Beach, California.
• Base salary is listed as $75,000 in Denver or $80,000 in Long Beach.
• U.S. work authorization eligibility is required for government and space-technology work.