Description
As a Lead Software Engineer, Perception (Robotics) at Grab, you will build and ship systems that turn raw multi-sensor data into a reliable, real-time and predictive representation of the world.
You will work across a robust modular perception stack and modern learning-based approaches, contributing through model development, evaluation, debugging, integration and on-robot validation.
Your responsibilities include:
- Developing and improving multi-object tracking
- Building and hardening generic / open-set world understanding
- Building motion prediction for pedestrians, cyclists, vehicles and other agents
- Developing and evaluating end-to-end temporal perception-prediction approaches
- Exploring VLM / VLA and embodied foundation models for open-vocabulary perception
- Strengthening multi-sensor and temporal integration
- Defining quality gates across tracking, prediction, and generic-object / occupancy / occupancy-flow recall
- Partnering with Detection, Prediction, Planning, Data & Infra, and Integration teams
Requirements:
- At least 3 years hands-on experience shipping or operating perception and / or prediction systems for robotics, AV or ADAS
- Rich experience across classical / geometric and learning-based approaches
- Proven depth in multi-object tracking
- Hands-on experience with generic / open-set perception
- Hands-on depth in at least one modern temporal area
- Fundamentals in geometry and multi-sensor systems
- Proficiency in C++ and Python
- Experience navigating noisy production-like environments
- Self-motivated and dependable
- Demonstrated proficiency in leveraging AI tools and systems
Benefits:
- Term Life Insurance and comprehensive Medical Insurance
- GrabFlex benefits package
- Parental and Birthday leave
- Love-all-Serve-all (LASA) volunteering leave
- Confidential Grabber Assistance Programme