Research Engineer (Hierarchical Learning for Multi-ASVs)

Interested applicants are invited to apply directly at the NUS Career Portal. Please note your application will only be processed if you apply via NUS Career Portal.

NUS Career Portal link: https://careers.nus.edu.sg/job/Research-Engineer-%28Hierarchical-Learning-for-Multi-ASVs%29/33552-en_GB/

We regret that only shortlisted candidates will be notified.

Job Description

This position involves working on a project related to the planning and control of a team of autonomous surface vehicles, for collaborative manipulation tasks on the surface of water. The objective of this position includes contributing to model development, solution, and implementation of such collaborative controllers on actual platforms, first in simulation and then on hardware. The role involves the opportunity to work with the PI's team within the National University of Singapore, as well as a large industrial partner. The successful candidate will be self-motivated with an outstanding track record in robotics, control, computer science, or related disciplines, with a special focus on reinforcement learning, imitation learning, and generative motion modelling. The main research tasks for the project include but will not be limited to:

• Developing robust conventional and learning-based controllers for collaborative manipulation by a team of autonomous surface vehicles.
• Designing and implementing controllers in simulation and then on hardware with our partner

Qualifications

•             Background in robotics, control engineering, or a related field, with a working foundation in classical control theory alongside modern learning-based methods.

•             Excellent coding skills in Python with PyTorch, including reinforcement learning, imitation learning, and flow matching/diffusion-based generative models.

•             Experience designing hierarchical control architectures that combine high-level RL policies with generative motion models and low-level tracking controllers.

•             Familiarity with various conditioning architectures for generative sequence models.

•             Hands-on experience with robotics simulation platforms (e.g. Isaac Lab, MuJoCo) and sim-to-real transfer for deploying learned policies on hardware.

•             Good writing/spoken communication skills for the purpose of writing research reports and presentations