Lead Localization Engineer at Grab

About the Team: The Robotics Technology team is a core part of Grab's long-term vision to build urban embodied AI. Our engineers take full ownership of the product lifecycle: designing and manufacturing hardware in-house, developing control and machine‑learning systems, and rigorously testing in real-world conditions and production fleet operations. This is a fast-moving, multidisciplinary environment where software, hardware and data science experts collaborate to solve practical challenges at scale. We are executing an ambitious growth plan to expand our robotics fleet across cities over the coming years, and we are focused on delivering highly productive, safe and efficient robot delivery services that help address current delivery labor shortages. Based in Singapore and China, we offer opportunities to work on the latest autonomy, deploy solutions in complex environments, and directly influence the future of last‑mile logistics. If you're excited by tangible impact, large-scale systems and cross-functional engineering, you'll find meaningful challenges and rapid career growth here. Get to know the Role: As the core architect of "Spatial Intelligence" for our road-legal, high-dynamic autonomous platforms, you will lead automotive-grade SLAM technologies and the R&D of high-precision, robust, and cost-effective. Your work will directly determine the robot's ability to navigate autonomously and ensure safety at urban road speeds (e.g., residential areas, commercial streets, office parks), driving the system from prototype to large-scale commercial deployment. You will report to the Head of Engineering and will be working onsite at Grab office. The critical tasks you will perform 1. Core Algorithm R&D & Optimization (50%) • HD Map Fusion: Design and implement localization strategies that match real-time sensor data against High-Definition (HD) Vector Maps for lane-level precision. • Multi-modal Fusion: Lead the development of SLAM algorithms for large-scale, semi-structured environments, focusing on tightly-coupled localization and mapping architectures using LiDAR, Vision, Odometry, and IMU. • Scenario Robustness: Overcome unique last-mile challenges: filtering dense dynamic obstacles, resolving localization ambiguity in repetitive scenes, ensuring seamless Global Navigation Integrity, and focus on maintaining decimeter-level accuracy in "Urban Canyons" and under high-speed GNSS-denied conditions. • Cost-Efficient Solutions: Build SLAM solutions optimized for low-cost hardware (e.g., solid-state LiDAR, cameras) and ensure long-term map stability. 2. Engineering Excellence & Deployment (30%) • Performance Balancing: Lead the deployment on NVIDIA Orin, focusing on deterministic, low-latency output and Functional Safety (SOTIF) principles. • Production Implementation: Refactor code architecture for production; manage memory, power consumption, and coordinate with hardware teams on sensor selection, calibration, and temporal synchronisation. • Mapping Toolchain: Design and implement automated toolchains for map generation, updates, and cloud management to support rapid operational expansion.3. Closed-loop Iteration & Collaboration (20%) • Evaluation & Truth Systems: Build performance evaluation frameworks (using metrics like ATE and Loop Closure success rates) to drive continuous algorithm evolution via data loops. • System Synergy: Collaborate with Perception and Planning/Control teams to provide high-quality, low-latency pose estimation and semantic map data, enhancing overall motion intelligence.