Senior Perception & Prediction Engineer (Robotics)

About the role

Grab's Robotics Technology team is building urban embodied AI, from in-house hardware and control systems to real-world fleet testing. As a Senior Perception & Prediction Engineer based in Singapore, you will turn raw multi-sensor data into a reliable, real-time and predictive view of the world, working across a modular perception stack and learning-based approaches. You will deepen multi-object tracking, open-set world understanding and motion prediction, and help productionise temporal perception-prediction models and VLA / embodied foundation models. The role reports to the Senior Principal Perception & Prediction Engineer and is onsite.

Key responsibilities

• Develop and improve multi-object tracking, including data association, Bayesian filtering (Kalman / EKF / UKF), track lifecycle and ID stability, and move toward learned, joint detection-and-tracking and query / transformer-based trackers.
• Build generic, open-set world understanding: class-agnostic obstacle detection, occupancy grids / networks / BEV occupancy, clustering and learned generic-object branches.
• Build motion prediction for pedestrians, cyclists and vehicles, including multi-modal trajectory forecasting, interaction-aware prediction, occupancy flow, uncertainty estimation and interfaces to behaviour and planning.
• Develop and evaluate end-to-end temporal perception-prediction approaches while keeping modular baselines and production fallbacks.
• Explore VLM / VLA and embodied foundation models, test their grounding and robustness, and distil, quantise or adapt them for on-robot deployment.
• Strengthen multi-sensor and temporal integration across camera, LiDAR, radar and IMU, and define quality gates (e.g. MOTA, ADE / FDE, latency budgets).
• Partner with Detection, Prediction, Planning, Data & Infra and Integration teams to move capabilities from research to training, simulation, NVIDIA Orin / TensorRT deployment and production testing.

Required profile

• At least 3 years of hands-on experience shipping or operating perception and/or prediction systems for robotics, AV or ADAS, with strong autonomous-driving experience.
• Rich experience across classical/geometric and learning-based approaches, with judgement on modular, end-to-end and hybrid designs and safety fallbacks.
• Proven depth in multi-object tracking and hands-on experience with open-set perception and at least one modern temporal area (motion forecasting, streaming BEV, world models, etc.).
• Experience with noisy production environments, reproducible experiments, metrics, log-driven root-cause analysis and simulation/replay.
• Good to have: end-to-end perception, motion prediction, VLM/VLA and foundation-model adaptation and deployment experience.

Required skills

• Fundamentals of geometry and multi-sensor systems, including calibration and alignment diagnostics.
• Proficiency in C++ and Python, with production-quality code and real-time embedded awareness.
• Use of AI tools and systems to accelerate engineering and research.