Research Assistant (Generative Models for Multi-Agent Exploration)

NATIONAL UNIVERSITY OF SINGAPORE; Pasir Panjang; On-site; MYR 100,000 - 150,000; Full time

Job summary

A prestigious university in Singapore is seeking applicants for a project on multi-agent exploration and navigation. The ideal candidate should possess excellent coding skills in Python with experience using PyTorch, and should have abilities in simulations and deep learning model implementations. Responsibilities include managing projects and supervising students. Interested candidates should apply directly through the university's career portal.

Qualifications

• Proficient in coding with Python and using PyTorch for deep learning.
• Ability to conduct literature reviews and summarize findings.
• Experience with simulation tools like AirSIM and ROS Gazebo.

Responsibilities

• Manage projects focusing on multi-agent exploration and navigation.
• Supervise undergraduate and master's thesis students.

Skills

Excellent coding skills in python with pytorch

Literature review/summarizing skills

Simulations abilities (e.g., AirSIM, ROS Gazebo)

Experience with implementation of deep learning model on hardware

Experience publishing papers

Good writing/spoken communication skills

Job description

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

This project will focus on multi-agent exploration and navigation in unknown areas, where multiple autonomous robots (agents) are tasked with spreading over a given region to be explored, or to reach a given position and discover the world to do so as rapidly as possible. Throughout this work, we will assume that robots can communicate their observations (e.g., partial map of the environment) during search, via local or global communications, so they can update their representation of the domain online. These tasks will be approach using generative models (GM), e.g., diffusion models and/or matching flows, to allow agents to generate medium- to longer-term plans that allow them to better trade off exploration and exploitation in the long run.

Qualifications

• Excellent coding skills in python with pytorch (distributed deep reinforcement learning, Transformers, etc.)

• Literature review/summarizing skills

• Simulations abilities (e.g., AirSIM, ROS Gazebo)

• Experience with implementation of deep learning model on hardware (e.g., ground/aerial robots)

• Experience publishing papers, and supervising undergraduate/master’s students

• Good writing/spoken communication skills