Software Engineer (Perception)

Lodestar as a Software Engineer - Perception, where you'll work on cutting-edge algorithms for real-time detection and classification of unknown space targets. You'll develop custom models that form the foundation for autonomous decision-making in complex space environments.

Responsibilities

• Your responsibilities will include scoping architecture for the perception system, researching and adapting novel perception algorithms, designing and developing ML algorithms, and integrating perception models into mission simulation environments.
• You should have at least 2 years of experience in machine learning, robotics, or computer vision, and be proficient in C++ and Python.
• Researching and building algorithms to detect, classify, and understand unknown space targets in real-time.
• Designing, developing, and optimizing machine learning algorithms for perception systems, including custom models for edge computing.
• Integrating perception models into mission simulation environments and real-time autonomy pipelines, and collaborating across teams to ensure performance and scalability.

Requirements

Excellent software engineering skills in C++ and Python

• Broad understanding of modern perception systems and their architecture
• Comfortable with containerization tools such as Docker and Kubernetes

Preferred

• Experience developing and deploying ML models to real-time systems
• 2+ years of distinguished industry experience in Machine Learning, robotics, computer vision, or a related field
• Bachelor’s or Master’s degree in, AI/ML, Computer Science, Robotics, a related field, or equivalent experience
• Strong DNN/ML background and experience in CV and image processing libraries (OpenCV, CUDA-accelerated vision, PCL)
• Strong understanding of networking and communication protocols for distributed autonomy systems

Experience with Linux, Git, and CI/CD pipelines

• Experience with distributed training and cloud-based scaling of ML models (AWS, GCP, or Azure)
• Track record optimizing neural networks and geometric algorithms using CUDA kernels, TensorRT, or other GPU acceleration frameworks
• Familiarity with image processing techniques (e.g., feature extraction, segmentation, filtering, stereo matching) to support 3D reconstruction and target classification
• Experience processing sensor measurements from a variety of sensors including RADAR, electro-optical sensors, RF sensors, or LIDAR

Pay

USD 115,000 - 180,000