Principle Engineer, 3D Reconstruction

Job description

Before the detail, here's the challenge you'd help us solve. We build the embodied intelligence that moves real vehicles safely, and the ecosystem a billion machines will run on in the future. Very few people in AI can say this. Every role here, whatever the team, plugs into that. Here’s what this particular role covers. 🛠️ About our Robotics Team The Robotics team is responsible for bridging the gap from our model to our vehicle platforms, in order to let the model focus on making driving decisions. We aim to provide high quality data to the model for making such decisions, whilst abstracting away platform-specific aspects. 🧠 Your day-to-day - Define the technical architecture and roadmap for Wayve’s offline 3D reconstruction system. - Lead the development of MVPs that unblock high-priority internal use cases, while guiding the transition to a robust internal platform. - Establish the core technical interfaces, output representations, and tools needed to support internal customers. - Partner with calibration, sensor fusion, perception, data, infrastructure, and validation teams to align requirements, resources and ownership boundaries. - Set technical standards for reconstruction quality, failure analysis, uncertainty measurement, and dataset suitability and execute strategies to validate them - Mentor and provide technical leadership to engineers contributing to the 3D reconstruction effort. - Communicate technical tradeoffs, limitations, and progress clearly to engineering leaders and cross-functional stakeholders. 🧩 What you’ll be working on: Leading the development of an offline 3D reconstruction capability that builds high-quality 3D world geometry from vehicle sensor data in dynamic scenes. The system will draw on localization and mapping, state estimation, and sensor fusion to produce offline 3D geometric reconstructions and best-estimate ego motion from heterogeneous vehicle platforms and sensor suites. The work will support internal validation, data enrichment, and model development by turning raw sensor data into reliable, quality-assessed 3D ground-truth outputs. This is a principal-level technical leadership role for someone who can set the technical direction, build early prototypes, and align cross-functional teams around a shared reconstruction capability. 🙌 You should apply if you have: Required Skills/Experience - Deep technical expertise in SLAM, 3D reconstruction, mapping, state estimation, or closely related robotics/perception fields. - Strong hands-on experience with lidar-based reconstruction, point-cloud registration, pose estimation, and real-world robotics sensor data. - Experience building offline reconstruction, mapping, or perception systems that operate on large volumes of sensor data. - Strong software engineering skills in C++, Python, or similar robotics/perception environments. - Experience taking research or prototype algorithms into reliable production systems. - Comfortable defining technical strategy, roadmaps, and milestones in ambiguous problem spaces - Strong cross-functional technical leadership in ambiguous, multi-team environments. - Clear communication of algorithmic tradeoffs, limitations, confidence, and failure modes to technical and cross functional stakeholders. - Systems-level understanding of sensor calibration, timing, synchronization and quality issues, and ability to define requirements and work with specialist teams to achieve them Desired Skills/Experience - MS/PhD in Robotics, Computer Science, State Estimation, Sensor Fusion, SLAM, 3D Reconstruction, or a related technical field; or equivalent practical experience. - Experience with autonomous vehicles, robotics, mapping, or ground-truth data pipelines in a production setting. - Experience with GNSS/INS fusion, sensor based odometry, or other high-accuracy position estimation approaches - Experience with nonlinear optimization techniques such as pose graph optimization, factor graphs, bundle adjustment, ICP etc - Experience apply modern machine learning approaches to 3D reconstruction, mapping, or scene understanding, including foundation models or learned 3D representations - Familiarity with robotics tooling such as ROS, PCL, OpenCV, CUDA, or similar. - Familiarity with ML data enrichment, autolabelling, annotation workflows, or validation-data generation. - Experience designing quality metrics, validation evidence, or credibility arguments for reconstructed data. - Experience leading small expert technical teams from early-stage concept to production use. 🌱 Not ticking every box? That’s totally okay! If you’re passionate about autonomy and keen to learn, we encourage you to apply even if you don’t meet every requirement. More about Wayve: 🚀 Wayve is building the leading AI platform for autonomous driving. We are pioneering an end to end AI approach that enables vehicles to learn directly from real world experience,