Autonomous Spacecraft Perception Engineer I

Menlo Ventures; Laguna Beach (CA); On-site; USD 75,000 - 80,000; Full time

Job summary

True Anomaly seeks an entry-level engineer to blend classical perception with modern ML for autonomous spacecraft. You will implement Kalman filters, train PyTorch models, and write C++ flight code, deploying algorithms on space-qualified hardware.

This 3‑month temporary engagement offers potential conversion based on performance and business needs. Work will be near Centennial, CO or Long Beach, CA.

Qualifications

• Pursuing or recently completed Bachelor's or Master's in computer science, electrical engineering, robotics, aerospace engineering, or related field
• Coursework in computer vision and estimation theory
• Proficiency in Python; some exposure to C++ (we'll teach you more)
• Familiarity with Kalman filters and data association OR deep learning (PyTorch)
• Understanding of linear algebra, probability, and coordinate transformations
• Ability to read research papers from robotics and ML conferences and implement algorithms
• Strong debugging skills and eagerness to learn the intersection of classical perception and ML
• U.S. Citizen (required for facility access and government contracts)

Responsibilities

• Implement classical tracking algorithms: Extended Kalman Filters for state estimation, Hungarian data association, and track management logic
• Train neural networks for detection and classification (YOLO, ResNet-based classifiers)
• Build hybrid perception pipelines: detections -> tracking -> coordinate transforms -> angle measurements for navigation
• Develop image processing chains: hot pixel filtering, adaptive thresholding, centroiding, CC analysis, star catalog matching
• Deploy models to edge hardware: quantize networks (INT8), integrate with ONNX Runtime/TensorRT
• Implement coordinate transformations: pixel -> camera -> body -> ECI with lens distortion and attitude considerations
• Generate synthetic data: Blender rendering with domain randomization
• Validate end-to-end performance with software-in-the-loop and hardware-in-the-loop tests

Skills

Python

C++ exposure

Kalman filters

Data association

PyTorch

OpenCV

Education

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

Tools

ONNX Runtime

TensorRT

Blender

Job description

True Anomaly seeks an entry-level engineer to blend classical perception with modern ML for autonomous spacecraft. You will implement Kalman filters, train PyTorch models, and write C++ flight code, deploying algorithms on space-qualified hardware.

This 3‑month temporary engagement offers potential conversion based on performance and business needs. Work will be near Centennial, CO or Long Beach, CA.