Senior Perception & Prediction Engineer - Robotics

Grab; Singapore; On-site; SGD 120,000 - 190,000; Full time

Benefits offered by this job

Term Life Insurance

Medical Insurance

GrabFlex

Parental leave

Birthday leave

LASA volunteering leave

Grabber Assistance Programme

FlexWork hours

Job summary

Grab in Singapore is seeking a Senior Perception & Prediction Engineer to build real-time multi-sensor perception for robotics and autonomous delivery systems. You will contribute to tracking, world understanding, motion forecasting, and end-to-end temporal models while ensuring robust safety and production-grade reliability.

You will collaborate with Detection, Prediction, Planning, Data & Infra teams to move research into reproducible training, replay, simulation, and on-robot deployment on

Qualifications

• At least 3 years hands-on experience shipping or operating perception and/or prediction systems for robotics, AV or ADAS, with strong autonomous-driving experience and a record of improving real-world performance.
• Rich experience across classical / geometric and learning-based approaches, with sound judgement on modular vs end-to-end designs and safety fallbacks.
• 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 and occupancy representations.
• Hands-on depth in motion forecasting, occupancy flow, streaming BEV, learned world models, or joint detection–tracking–prediction.
• Fundamentals in geometry and multi-sensor systems, including practical calibration know-how and timing issues.
• Proficiency in C++ and Python, with production-quality code and real-time embedded performance.

Responsibilities

• Develop and improve multi-object tracking — data association, Bayesian state estimation, track lifecycle, and ID stability across detector gaps and occlusions.
• Build generic/open-set world understanding — obstacle detection, occupancy grids, BEV occupancy representations and learned branches.
• Develop motion prediction for pedestrians, cyclists, vehicles, with multi-modal trajectory forecasting and uncertainty estimation.
• Evaluate end-to-end temporal perception-prediction approaches while maintaining strong modular baselines and production fallbacks.
• Explore VLM/VLA and embodied foundation models for open-vocabulary perception and grounded reasoning.
• Strengthen multi-sensor and temporal integration across camera, LiDAR, radar and IMU.
• Define quality gates across tracking, prediction, and embedded latency budgets with fleet data analytics.
• Collaborate with Detection, Prediction, Planning, Data & Infra teams to move capabilities from research to production.

Skills

C++

Python

Tracking

Prediction

Sensor fusion

Temporal modeling

Open-set perception

Model debugging

Tools

OpenCV

PCL

ROS 2

NVIDIA Orin

TensorRT

DeepStream

BEV

Kalman filter

Job description

Grab in Singapore is seeking a Senior Perception & Prediction Engineer to build real-time multi-sensor perception for robotics and autonomous delivery systems. You will contribute to tracking, world understanding, motion forecasting, and end-to-end temporal models while ensuring robust safety and production-grade reliability.

You will collaborate with Detection, Prediction, Planning, Data & Infra teams to move research into reproducible training, replay, simulation, and on-robot deployment on