8 hours ago
Singapore, SingaporeSenior
Responsibilities
- Design and implement deep learning models for visual navigation, Vision-Language Navigation, and visual place recognition.
- Develop multimodal perception pipelines using RGB, depth, semantic segmentation, and language-conditioned navigation signals.
- Research scene understanding, end-to-end learning, and modular navigation architectures for dynamic urban environments.
- Implement and adapt VLN and visual navigation algorithms for deployment on physical robot hardware.
- Build performance evaluation frameworks and benchmarks for outdoor last-mile delivery scenarios.
- Collaborate with perception, planning/control, hardware, and systems teams to integrate and validate navigation capabilities.
- Drive closed-loop dataset collection and annotation pipelines and support sensor selection, calibration, and data quality.
- Publish research, present findings, contribute to repositories, and help shape the research roadmap.
Requirements
- PhD in Computer Science, Robotics, AI, Computer Vision, or a closely related field.
- Strong publication record or demonstrable research contributions in Visual Navigation, Vision-Language Navigation, Embodied AI, or Robot Perception.
- Proficiency in at least two areas including VLN, visual place recognition/localisation, deep learning for perception, or reinforcement learning for navigation.
- Familiarity with VLN benchmarks such as R2R, REVERIE, and SOON; instruction-following models; and cross-modal grounding.
- Experience with Python and PyTorch, JAX, or TensorFlow, plus ROS or ROS 2 for robot integration.
- Ability to design, execute, and critically evaluate experiments and communicate findings through reports and publications.
- Preferred experience deploying learned navigation models on physical robots, LiDAR-visual fusion, hybrid metric-topological navigation, vision-language models for robotic instruction following, autonomous vehicle or robotics research, and AI research tools.
Benefits
- Term Life Insurance and comprehensive Medical Insurance.
- GrabFlex flexible benefits package.
- Parental leave, Birthday leave, and Love-all-Serve-all volunteering leave.
- Confidential Grabber Assistance Programme.
- Onsite work at Grab’s One North office in Singapore.
Categories
ML EngineeringRobotics
About Grab
Grab builds a Southeast Asia superapp for mobility, deliveries, and financial services, serving consumers, drivers, merchants, and enterprises. It monetizes via ride and delivery commissions, merchant services (such as ads and subscriptions), and payments and digital banking products. Founded in 2012 and headquartered in Singapore, Grab operates across multiple Southeast Asian markets and is publicly listed on NASDAQ.