Interested applicants are invited to apply directly at the NUS Career Portal

Your application will be processed only if you apply via NUS Career Portal

We regret that only shortlisted candidates will be notified.

Job Description

The Collaborative Learning and Adaptive Robotics (CLeAR) Lab at National University of Singapore (NUS), is seeking a motivated Research Assistant to support research in embodied intelligence, robot learning, and generalizable navigation. The position focuses on developing algorithms that enable robots to understand, localize, and navigate in open-world dynamic environments

The successful candidate will work closely with faculty and graduate researchers to design, implement, and evaluate new learning-based approaches that integrate perception, mapping, and planning for autonomous systems. This position provides an opportunity to contribute to high-impact research and publications in leading robotics and AI venues

Key Responsibilities

• Design and implement algorithms for robot perception, mapping, and navigation in open-world unstructured and dynamic environments.
• Develop experimental pipelines integrating computer vision, machine learning, and robotic control components using Python and ROS 2.
• Conduct quantitative evaluations, analyze results, and assist in preparing datasets and benchmarks for research experiments.
• Collaborate on the preparation of manuscripts, reports, and technical documentation for conference and journal submissions.
• Contribute to lab infrastructure by maintaining codebases, experiment logs, and reproducible workflows

Only shortlisted candidates will be notified.

Job Requirements

• Bachelor's or higher degree in Computer Science, Electrical Engineering, Robotics, or a related field.
• Strong programming skills in Python, with experience in PyTorch, ROS / ROS 2, and computer vision or perception systems.
• Solid understanding of machine learning, deep learning, and robot perception concepts.
• Demonstrated ability to carry out independent research or project work involving algorithm design and empirical evaluation.
• Excellent communication, documentation, and teamwork skills.

Preferred Qualifications

• Demonstrated experience in robot navigation and mapping, or embodied AI research.
• Familiarity with large-scale dataset annotation and multi-modal sensing pipelines (e.g., RGB-D, LiDAR, IMU) and/or real-robot experimentation.
• Hands-on experience with robot simulation environments, such as Gazebo, Isaac Sim, or Habitat.
• Exposure to foundation models (e.g., VLMs, LLMs) applied to robotic perception or planning.
• Publications or active submissions in relevant areas (robotics, machine learning, computer vision, or embodied AI) are a strong plus.