Space Systems Software Engineer I: Vision & Estimation

Socket.dev; Denver (CO); On-site; USD 75,000 - 80,000; Full time

Job summary

True Anomaly seeks a motivated student or recent graduate to join a hybrid perception team for autonomous spacecraft. You will blend classical computer vision with ML to build multi-object tracking pipelines and develop Kalman filtering, transforming coordinates from pixels to orbital frames.

You will implement EKFs, train networks in PyTorch, and integrate with C++ flight code, delivering algorithms for space-qualified processors in a three-month engagement with potential conversion.

Qualifications

• Pursuing or completed Bachelor's or Master's in a technical field related to CS/EE/Robotics/Aerospace.
• Coursework in vision and estimation theory or willingness to learn both.
• Proficiency in Python; some exposure to C++.
• Familiarity with either classical tracking (Kalman filters, data association) OR deep learning (PyTorch, training neural networks).
• Understanding of linear algebra, probability, and coordinate transformations.
• Ability to read research papers and implement algorithms from robotics and ML venues.
• Strong debugging skills and eagerness to learn the intersection of classic perception and ML.

Responsibilities

• Implement Extended Kalman Filters for state estimation.
• Train neural networks for detection and classification (YOLO, ResNet).
• Build hybrid perception pipelines: detections → tracking → coordinates → angle measurements.
• Develop image processing chains (thresholding, centroiding, connected components).
• Deploy models to edge hardware (quantize, integrate with ONNX Runtime/TensorRT) and optimize for space-qualified processors.
• Implement coordinate transformations: pixel → camera → body → Earth-Centered Inertial (ECI).
• Generate synthetic data with Blender/Unreal and domain randomization.
• Validate end-to-end with software-in-the-loop and hardware-in-the-loop testing.

Skills

Python

C++

PyTorch

OpenCV

Kalman Filters

Data association

Tracking

Coordinate transforms

Education

Bachelor's or Master’s in CS/EE/Robotics/Aerospace

Tools

ONNX Runtime

TensorRT

Jetson

ROS

CUDA

ONNX

Job description

True Anomaly seeks a motivated student or recent graduate to join a hybrid perception team for autonomous spacecraft. You will blend classical computer vision with ML to build multi-object tracking pipelines and develop Kalman filtering, transforming coordinates from pixels to orbital frames.

You will implement EKFs, train networks in PyTorch, and integrate with C++ flight code, delivering algorithms for space-qualified processors in a three-month engagement with potential conversion.