Software Engineer: Perception

<h3>About Lodestar</h3> <p>Lodestar's mission is to develop the first "Protect and Defend" capability for high-value space assets in orbit. Our flagship product<span class="Apple-converted-space"> </span><em>MITHRIL</em><span class="Apple-converted-space"> </span>is the critical hardware & software necessary to augment any off-the-shelf spacecraft with the ability to autonomously detect, characterise, and reversibly neutralise orbital threats. By building on the proven space heritage of our best-in-class satellite-bus partners and fully integrating<span class="Apple-converted-space"> </span><em>MITHRIL</em><span class="Apple-converted-space"> </span>as a single platform, we deliver a fully autonomous end-to-end protection spacecraft service.</p> <h3><strong>About the Job</strong></h3> <p>As a<span class="Apple-converted-space"> </span><strong>Software Engineer - Perception</strong><span class="Apple-converted-space"> </span>at Lodestar, you’ll be joining the perception and machine vision teams to rapidly grow our vision and perception models at<span class="Apple-converted-space"> </span><em>MITHRIL’s</em><span class="Apple-converted-space"> </span>center. You’ll focus on researching and building algorithms to detect, classify and understand unknown space targets in real-time. By combining computer vision, image processing and machine learning, you’ll develop custom models - providing the foundation for autonomous decision-making in complex and uncertain space environments.</p> <p>We proudly have an "extreme ownership" oriented engineering culture. </p> <hr> <h3><strong>What You’ll Do</strong></h3> <ul> <li>Scoping architecture for the perception system core to Lodestar’s autonomy software suite</li> <li>Research and adapt novel perception algorithms - everything from lit. review, through training and evaluation, to optimisation and deployment</li> <li>Design, develop ML algorithms from the ground up, in addition to build on and optimizing our existing models for edge computing</li> <li>Further develop our robust methods for predicting relative pose of dynamic space targets in harsh and unpredictable visual environments</li> <li>Integrate perception models into mission simulation environments and real-time autonomy pipelines</li> <li>Contribute to the design of realistic sensor models and digital twins to improve perception fidelity in mission scenarios</li> <li>Own perception tooling, model training infrastructure, and evaluation fra