Senior Perception Engineer

Senior Perception Engineer — Autonomous Driving (L4 Heavy-Duty Trucks)

Team: Autonomous Driving · Perception

Location: Singapore

Employment type: Full-time

About the Role

We are building full-stack Level 4 autonomous driving systems for heavy-duty trucks in highway and trunk logistics, and we are standing up our overseas perception team. This is an early, high-ownership role: you will help architect the perception stack for our global product.

Heavy trucks are not passenger cars. At highway speed and full load, stopping distances stretch well beyond 100 meters, so our perception system has to see farther, earlier, and more reliably than a typical robotaxi stack. If you want to solve long-range, high-speed perception problems that genuinely matter for safety — and see them deployed on real freight lanes at scale — this is the place.

What You’ll Do

• Architect and develop the multi-modal perception stack (camera, LiDAR, radar) for L4 highway trucking.
• Build long-range 3D object detection (300 m+), tracking, classification, semantic/instance segmentation, drivable-area/free-space estimation, and lane and road-structure perception.
• Design sensor-fusion approaches (BEV/occupancy/late fusion) tuned for the geometry and dynamics of heavy trucks.
• Push the stack toward end-to-end, learned perception, and contribute to the broader shift from modular pipelines toward end-to-end autonomous driving.
• Train, optimize, and deploy deep-learning models on automotive-grade compute (e.g., NVIDIA DRIVE Orin/Thor) under hard real-time constraints — quantization, pruning, TensorRT.
• Tackle highway long-tail scenarios: cut-ins, stalled/slow vehicles, road debris, construction zones, and adverse weather and lighting.
• Build perception with safety in mind, working with our safety team on functional-safety and SOTIF considerations where relevant.
• Help establish team engineering practices, mentor engineers, and collaborate closely with planning, control, mapping, data, and platform teams.

What We’re Looking For

• MS or PhD in Computer Science, EE, Robotics, Applied Math, or equivalent practical experience.
• Strong fundamentals in computer vision and deep learning.
• Hands-on experience with modern 3D perception: point-cloud detection (e.g., PointPillars, CenterPoint), BEV/transformer-based perception, occupancy networks.
• Eagerness to grow toward end-to-end, learned perception. You don’t need to have shipped an end-to-end stack — but you should be excited to move in that direction as the field and our system evolve, with the DL foundation to get there.
• Solid grasp of multi-object tracking and multi-sensor fusion.
• Proficient in C++ and Python, comfortable working under real-time/embedded constraints.
• Experience deploying DL models to automotive or edge compute (TensorRT, CUDA, model optimization).
• Working knowledge of camera/LiDAR/radar sensor modalities.

Nice to Have

• Production autonomous-driving/ADAS experience, ideally shipped to vehicles.
• Commercial-vehicle or heavy-truck AV experience.
• Long-range/high-speed perception experience.
• Foundation-model perception, occupancy networks, or other emerging architectures.
• Large-scale data-engine work: auto-labeling, active learning, mining.
• Familiarity with functional safety (ISO 26262) or SOTIF (ISO 21448).
• NVIDIA DRIVE platform (Orin/Thor) and embedded/AUTOSAR-adjacent experience.
• Top-venue publications (CVPR/ICCV/ECCV/NeurIPS/CoRL).

Why Join Us

• L4, not L2 — full self-driving for commercial trucking, not driver-assist.
• Real deployment at scale on commercial freight lanes, with a fast feedback loop from road to model.
• A global, founding-stage team where your architectural decisions set the direction.