Perception Engineer

<h2><strong>Perception Engineer&nbsp;</strong></h2> <p><strong>Company:</strong><span style="font-weight: 400;"> Vatn Systems</span></p> <p><strong>Location:</strong><span style="font-weight: 400;"> Bristol, RI</span></p> <p><strong>Type:</strong><span style="font-weight: 400;"> Onsite</span></p> <p><strong>About Vatn Systems:</strong></p> <p><span style="font-weight: 400;">Vatn Systems is an innovative startup at the forefront of designing and manufacturing autonomous underwater vehicles (AUVs). Our mission is to revolutionize underwater security, exploration, research, and operations through cutting-edge technology and unparalleled engineering. Our AUVs are defining the next generation of underwater autonomy.</span></p> <h2><strong>The Role</strong></h2> <p><span style="font-weight: 400;">As a Perception Engineer, you'll develop and improve the perception stack that powers our self-driving vehicles. Working hands-on with sonar and image data, you'll help build robust pipelines for detecting and tracking. You'll work closely with the autonomy team to integrate perception capabilities into bespoke behaviors, unlocking novel capabilities. </span></p> <h2><strong>What You'll Do</strong></h2> <ul> <li style="font-weight: 400;"><span style="font-weight: 400;">Implement and maintain real-time perception pipelines on autonomous vehicle platforms.</span></li> <li style="font-weight: 400;"><span style="font-weight: 400;">Develop algorithms for obstacle detection, classification, and multi-object tracking.</span></li> <li style="font-weight: 400;"><span style="font-weight: 400;">Write and maintain ROS 2 nodes and packages for on-vehicle perception software.</span></li> <li style="font-weight: 400;"><span style="font-weight: 400;">Utilize Python and C++ to develop and implement algorithms for obstacle detection, classification, and multi-object tracking.</span></li> <li style="font-weight: 400;"><span style="font-weight: 400;">Participate in on-site vehicle testing and debugging of real-world perception failures.</span></li> <li style="font-weight: 400;"><span style="font-weight: 400;">Collaborate with localization, prediction, and planning teams to ensure clean perception interfaces.</span></li> </ul> <h2><strong>What We're Looking For</strong></h2> <p><strong>Required</strong></p> <ul> <li style="font-weight: 400;"><span style="font-weight: 400;">3–5 years of experience in robotics perception, computer vision, or autonomous systems.</span></li> <li style="font-weight: 400;"><span style="font-weight: 400;">Strong </span><strong>Python</strong><span style="font-weight: 400;"> skills for prototyping, scripting, and ML workflows.</span></li> <li style="font-weight: 400;"><span style="font-weight: 400;">Solid </span><strong>ROS / ROS 2</strong><span style="font-weight: 400;"> experience, experience with commercial grade robotic systems.</span></li> <li style="font-weight: 400;"><span style="font-weight: 400;">Proficient in </span><strong>C++</strong><span style="font-weight: 400;"> for real-time, production-grade robotics software.</span></li> <li style="font-weight: 400;"><span style="font-weight: 400;">Experience with 3D sensor data — LiDAR point clouds, depth estimation, or multi-sensor fusion. Marine sensor experience is a big plus!</span></li> <li style="font-weight: 400;"><span style="font-weight: 400;">Working knowledge of deep learning frameworks (PyTorch preferred) for detection or segmentation tasks.</span></li> <li style="font-weight: 400;"><span style="font-weight: 400;">Working knowledge of classical data-driven perception techniques.</span></li> <li style="font-weight: 400;"><span style="font-weight: 400;">Understanding of 3D geometry, sensor calibration, and coordinate frame transformations.</span></li> <li style="font-weight: 400;"><span style="font-weight: 400;">Willingness to work on-site and participate in physical vehicle test sessions.</span></li> <li style="font-weight: 400;"><span style="font-weight: 400;">US Citizen and ability to gain a security clearance.</span></li> </ul> <p><strong>Preferred</strong></p> <ul> <li style="font-weight: 400;"><span style="font-weight: 400;">Exposure to </span><strong>Rust</strong><span style="font-weight: 400;"> for systems programming or robotics tooling.</span></li> <li style="font-weight: 400;"><span style="font-weight: 400;">Familiarity with AV-specific perception challenges: moving object tracking, occlusion handling, sensor degradation in adverse weather, GPS-denied localization.</span></li> <li style="font-weight: 400;"><span style="font-weight: 400;">Knowledge of TensorRT or other inference optimization tools for real-time deployment.</span></li> <li style="font-weight: 400;"><span style="font-weight: 400;">Understanding of AV safety standards or safety-critical software development practices.</span></li> </ul> <h2><strong>Nice to Have</strong></h2> <ul> <li style="font-weight: 400;"><span style="font-weight: 400;">Prior experience at a startup and/or defense company.</span></li> <li style="font-weight: 400;"><span style="font-weight: 400;">Experience deploying perception models on embedded automotive hardware (Drive AGX, Jetson, etc.).</span></li> </ul>