Job Description

Get to Know the Team

Our team develops production-grade robotics and autonomy capabilities for the uniquely complex, unstructured urban environments of Southeast Asia. We are ambitious and pragmatic: advancing perception, planning, and control step by step, with safety evidence as the gate for every milestone. We focus on building robust system capabilities, scaling with uncompromised quality, and collaborating with industry leaders while investing in in-house expertise where it differentiates us.

We are a senior, hands-on engineering group that prizes operational excellence, clear interfaces, and reproducible pipelines.

Get to Know the Role

As the Principal Prediction Engineer, you will be the technical anchor for behavior forecasting. Your mission is to architect and deliver the systems that predict the future motion of all dynamic agents in complex, real-world environments. You will own the development of machine learning models that are core to our platform's ability to anticipate and interact safely within these dynamic scenes. This is a deeply technical, hands-on role that bridges the gap between perception and decision-making.

You will report to the Head of Engineering and will contribute directly to both technical and strategic leadership. This is a fully onsite role at Grab Singapore's One North office.

The Critical Tasks You Will Perform

Architecture & Technical Strategy

• Lead the development and training of state-of-the-art deep learning models for trajectory forecasting and behavior classification, with a focus on intent detection and handling long-tail edge cases (e.g., recognizing subtle cues from other agents and anticipating emergency maneuvers).
• Own the architecture of a robust, scalable prediction engine designed to handle the unique, highly-interactive behaviors found in dense Southeast Asian urban environments.
• Define the validation strategy for the prediction system, ensuring its outputs are reliable, well-calibrated, and safe for downstream consumption.
• Lead design reviews and drive best practices for developing, validating, and deploying safety-critical machine learning models.

Algorithm & Model Development

• Lead the development and training of state-of-the-art deep learning models for trajectory forecasting and behavior classification.
• Own the core modeling choices, from defining evaluation metrics and loss functions to the final network architecture and inference logic.
• Partner with our MLOps and infrastructure teams to steer the development of data pipelines and training frameworks that meet the specific needs of your models.

Integration & Collaboration

• Partner deeply with the Planning team to understand their requirements, ensuring prediction outputs are well-integrated and directly improve system performance.
• Work closely with the Perception team to define the inputs and interface contracts required to feed the prediction models.
• Act as a technical mentor and sounding board to other engineers, elevating the team's expertise in machine learning, data science, and probabilistic modeling.

Job Requirements