8 hours ago
Shanghai, ChinaMid Level
Responsibilities
- Develop multi-object tracking using data association, Bayesian state estimation, Kalman/EKF/UKF filtering, motion models, track lifecycle management, and learning-based trackers.
- Build generic/open-set perception, occupancy representations, class-agnostic obstacle detection, clustering, and unknown-object handling.
- Develop motion prediction for pedestrians, cyclists, vehicles, and other agents using multimodal forecasting, interaction-aware prediction, occupancy flow, and uncertainty estimation.
- Evaluate temporal perception-prediction systems, VLM/VLA and embodied foundation models, grounding, hallucination, latency, robustness, and on-robot deployment suitability.
- Integrate camera, LiDAR, radar, and IMU data while maintaining geometric, temporal, identity, prediction, and semantic consistency.
- Define quality gates and investigate regressions using fleet logs, simulation, replay, closed-loop safety outcomes, and embedded latency budgets.
- Partner with Detection, Prediction, Planning, Data & Infra, and Integration teams to move systems from research into reproducible training and production-like robot testing.
Requirements
- At least 3 years of hands-on experience shipping or operating perception and/or prediction systems for robotics, autonomous vehicles, or ADAS, with strong autonomous-driving experience.
- Rich experience with classical/geometric and learning-based approaches, including judgment about modular, end-to-end, hybrid, and interpretable safety-fallback designs.
- Proven depth in multi-object tracking, data association, Bayesian filtering, track lifecycle, multi-sensor/temporal association, ID stability, and low-latency evaluation.
- Hands-on experience with generic/open-set perception, class-agnostic obstacle detection, occupancy representations, LiDAR clustering, anomaly or unknown-object handling, or learned-detection fusion.
- Depth in at least one temporal area such as motion forecasting, occupancy flow, streaming/temporal BEV, learned world models, or joint detection-tracking-prediction.
- Fundamentals in geometry and multi-sensor systems, including calibration and diagnosis of alignment or time-synchronization issues.
- Proficiency in C++ and Python for production-quality code, training/evaluation tools, and real-time embedded performance analysis.
- Experience with reproducible experiments, metrics, log-driven root-cause analysis, simulation/replay, and validation-oriented execution.
- Preferred experience includes VLM/VLA and embodied foundation models, model adaptation and deployment, 3D/BEV detection, sensor fusion, robotics/perception libraries, edge inference, and model lifecycle practices.
- Demonstrated ability to use AI tools and systems to accelerate engineering and research while maintaining quality, security, and reproducibility.
Benefits
- Term Life Insurance and comprehensive Medical Insurance.
- GrabFlex benefits package and Parental, Birthday, and Love-all-Serve-all volunteering leave.
- Confidential Grabber Assistance Programme.
- FlexWork arrangements including differentiated hours.
- The role is onsite at a Grab office and is based in Singapore or China.
Categories
ML EngineeringRobotics
About Grab
Grab builds a Southeast Asia superapp for mobility, deliveries, and financial services, serving consumers, drivers, merchants, and enterprises. It monetizes via ride and delivery commissions, merchant services (such as ads and subscriptions), and payments and digital banking products. Founded in 2012 and headquartered in Singapore, Grab operates across multiple Southeast Asian markets and is publicly listed on NASDAQ.