Principal Prediction Engineer

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 platforms 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 Singapores 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 teams expertise in machine learning data science and probabilistic modeling.

Qualifications :

What Essential Skills You Will Need

Essential Skills

• Extensive experience in machine learning with a proven track record of designing and shipping production-grade forecasting or behavior modeling systems for complex robotics or related intelligent systems.
• Expert-level proficiency in Python and deep learning frameworks (e.g. PyTorch TensorFlow).
• Strong proficiency in C for on-vehicle deployment and integration with the broader robotics stack.
• Deep understanding of modern ML architectures for sequential and relational data (e.g. LSTMs Transformers GNNs).
• Strong foundation in probability and statistics with experience in probabilistic modeling and representing uncertainty.
• Experience designing benchmarking or evaluation frameworks to compare prediction models across both offline datasets and real-world scenarios.
• Demonstrated leadership in the architecture and design of complex data-driven software systems.
• BS/MS/PhD in CS Robotics or a related field with a focus on Machine Learning or equivalent practical experience.

Preferred Skills

• Experience with interaction-aware forecasting models that explicitly reason about the influence between multiple agents.
• Experience optimizing ML models for high-performance embedded compute platforms for robotics (e.g. NVIDIA Jetson DRIVE or similar).
• Knowledge of causal inference model explainability (XAI) and other methods for building trustworthy safety-critical AI systems.
• Experience using simulation to generate training data or for large-scale model validation.
• A background in motion planning or control theory.
• Publications in top-tier machine learning or robotics conferences (e.g. NeurIPS ICML CVPR CoRL RSS).

Additional Information :

Life at Grab

We care about your well-being at Grab here are some of the global benefits we offer:

• We have your back with Term Life Insurance and comprehensive Medical Insurance.
• With GrabFlex create a benefits package that suits your needs and aspirations.
• Celebrate moments that matter in life with loved ones through Parental and Birthday leave and give back to your communities through Love-all-Serve-all (LASA) volunteering leave
• We have a confidential Grabber Assistance Programme to guide and uplift you and your loved ones through lifes challenges.
• Balancing personal commitments and lifes demands are made easier with our FlexWork arrangements such as differentiated hours

What We Stand For at Grab

We are committed to building an inclusive and equitable workplace that enables diverse Grabbers to grow and perform at their best. As an equal opportunity employer we consider all candidates fairly and equally regardless of nationality ethnicity religion age gender identity sexual orientation family commitments physical and mental impairments or disabilities and other attributes that make them unique.

Remote Work :

No

Employment Type :

Full-time