Software Engineer: Perception (II,III)

Lodestar•Los Angeles, CA

9d•$115,000 - $200,000

About The Position

Lodestar is hiring a mid-career Software Engineer II/III - Perception to join its perception and machine vision teams. The role contributes to the vision and perception models at the center of MITHRIL, Lodestar’s autonomous spacecraft protection platform. The engineer will help develop algorithms that detect, classify, and understand unknown space targets in real time, working alongside senior perception engineers on computer vision, image processing, and machine learning for autonomous decision-making in complex and uncertain space environments. The position offers early ownership with support for professional growth within an engineering culture oriented around “extreme ownership.” The engineer will contribute across the full lifecycle of perception algorithms, including research, training, evaluation, optimisation, and deployment. Responsibilities include improving models for edge computing, developing components with guidance from perception leads, supporting relative-pose prediction for dynamic space targets, integrating models into simulation and real-time autonomy pipelines, and maintaining perception tooling and infrastructure. The role collaborates with autonomy, estimation, and mission software teams.

Requirements

Solid software engineering skills in Python and working proficiency in C++.
Foundational DNN/ML knowledge and hands-on experience with computer vision or image processing libraries, such as OpenCV.
Bachelor's or Master's degree in AI/ML, Computer Science, Robotics, a related field, or equivalent experience.
2–5 years of professional experience in machine learning, robotics, computer vision, or a related field; internships, research placements, and substantial academic or personal projects count.
Demonstrated ability to take an ML model from training through evaluation in any setting, including coursework, research, or industry.
Broad understanding of modern perception systems and their architecture.
Exposure to sensor measurements from RADAR, electro-optical sensors, RF sensors, and/or LIDAR.
Experience developing or deploying ML models to real-time or resource-constrained systems.
For ITAR compliance, must be a U.S. citizen, lawful permanent resident of the U.S., protected individual as defined by 8 U.S.C. 1324b(a)(3), or eligible to obtain required authorizations from the U.S. Department of State.

Nice To Haves

Familiarity with image processing techniques such as feature extraction, segmentation, filtering, and stereo matching to support 3D reconstruction and target classification.
Experience optimising neural networks or geometric algorithms using CUDA kernels, TensorRT, or other GPU acceleration frameworks.
Exposure to distributed training or cloud-based scaling of ML models on AWS, GCP, or Azure.
Experience with Linux, Git, and CI/CD pipelines.
Comfort with containerisation tools such as Docker and Kubernetes.
Understanding of networking and communication protocols for distributed autonomy systems.

Responsibilities

Contribute to the perception system at the core of Lodestar's autonomy software suite.
Work through the full lifecycle of perception algorithms alongside senior engineers, including literature review, training, evaluation, optimisation, and deployment.
Build on and optimise existing models for edge computing, and develop new components with guidance from the perception leads.
Help develop and test methods for predicting the relative pose of dynamic space targets in harsh and unpredictable visual environments.
Integrate perception models into mission simulation environments and real-time autonomy pipelines.
Contribute to the design of realistic sensor models and digital twins to improve perception fidelity in mission scenarios.
Maintain and extend perception tooling, model training infrastructure, and evaluation frameworks.
Collaborate across the autonomy, estimation, and mission software teams to support perception fidelity, performance, and scalability.