Description

Grab is hiring a Senior Perception & Prediction Engineer to build and ship real-time perception and prediction systems for robot delivery. The role develops multi-object tracking, generic open-set world understanding, motion prediction, end-to-end temporal perception-prediction models, and VLM/VLA or embodied foundation-model capabilities, while maintaining modular baselines, safety fallbacks, and production-quality evaluation. The engineer will work across multi-sensor integration, embedded deployment, simulation, testing, and fleet-data validation, reporting to the Senior Principal Perception & Prediction Engineer and working onsite at a Grab office in Singapore or China.

Required Skills

Multi-object tracking
Bayesian filtering
Motion prediction
C++
Python
Sensor fusion
VLM/VLA

Additional Information

Required Previous Experiences: At least 3 years of hands-on experience shipping or operating perception or prediction systems for robotics, autonomous vehicles, or ADAS, with strong autonomous-driving experience and a record of improving real-world performance.
Proven depth in multi-object tracking, including data association, Bayesian filtering, track lifecycle, multi-sensor and temporal association, ID stability, and low-latency evaluation.
Hands-on experience with generic or open-set perception, including class-agnostic obstacle detection, occupancy representations, LiDAR clustering, and anomaly or unknown-object handling.
Hands-on depth in at least one modern temporal perception or prediction area, such as motion forecasting, occupancy flow, streaming or temporal BEV, learned world models, or joint detection-tracking-prediction.
Fundamentals in geometry and multi-sensor systems, including practical calibration and the ability to diagnose alignment or time-synchronisation issues.
Proficiency in C++ and Python, with the ability to write production-quality code, build training and evaluation tools, and reason about real-time embedded performance.
Experience navigating noisy production-like environments through reproducible experiments, clear metrics, log-driven root-cause analysis, simulation and replay, and validation-minded execution.
Preferred Qualifications: End-to-end perception and prediction, including joint detection-tracking-forecasting, occupancy or occupancy-flow prediction, streaming BEV, agent or trajectory queries, and world models.
Motion prediction for autonomous systems, including multi-modal trajectories, interaction-aware forecasting, uncertainty calibration, planning interfaces, and closed-loop simulation or behaviour evaluation.
Experience with VLM, VLA, or embodied foundation models, including vision-language grounding, open-vocabulary perception, task or instruction conditioning, semantic scene reasoning, and long-tail mining.
Foundation-model adaptation and deployment, including supervised fine-tuning, LoRA, distillation, quantisation, teacher-student pipelines, edge inference, and evaluation of hallucination and grounding.
3D or BEV detection and sensor fusion, temporal models, 4D data, and multi-camera, LiDAR, or radar integration.
Experience with robotics and perception libraries and platforms such as OpenCV, PCL, Ceres, ROS 2, NVIDIA Orin, TensorRT, or DeepStream, plus strong visualisation and debugging practices.
Familiarity with the model lifecycle, including dataset curation, auto-labeling, temporal annotation, active learning, regression detection, inference optimisation, and fleet-data feedback loops.
Translation Company Name: Grab

About Grab

Grab

View full company profile

Senior Software Engineer, Perception (Robotics) at Grab

Description

Required Skills

Additional Information

About Grab

Trending job searches

Get More from Metaintro

Ready to find a role that actually fits?

Required Skills

Additional Information

About Grab