Research Position Opening


We have a position opening for a Senior Research Fellow. An attractive remuneration based on the experiences and qualifications and a standard benefit package competitive with the industry will be provided for the successful applicant (see below for details). Singapore also offers a very low tax rate (Tax Payable is $550 on first $40,000 + 7% on next $40,000).


Virtual Singapore is a dynamic three-dimensional (3D) city model and collaborative data platform, including the 3D maps of Singapore. When completed, Virtual Singapore will be the authoritative 3D digital platform intended for use by the public, private, people and research sectors. It will enable users from different sectors to develop sophisticated tools and applications for test-bedding concepts and services, planning and decision-making, and research on technologies to solve emerging and complex challenges for Singapore. NTU was awarded funding to help develop computational models for use in the Virtual Singapore platform.


We are looking for a Senior Research Fellow to help develop computational techniques and models for the project. The successful candidate will also help to coordinate research activities in an exciting multidisciplinary project, in collaboration with Singapore General Hospital (SGH) and Singapore Civil Defence Force (SCDF), funded by National Research Foundation (NRF) under the Virtual Singapore (VS) program. The candidate will have the chance to work in a variety of areas including software development, data analytics, computational modelling, 3D visualisation, crowd dynamics, optimisation, machine learning.


Demonstrable achievements and skills in one or more of these areas is desirable.


Potential candidates are required to have:


      PhD Degree in Computer Science ore related field

      Strong scientific publication record

      Track record in research project management

      Strong programming skills on C++, Java, and Python

      Ability to work independently and with an international team

      Excellent analytical, technical and problem solving skills

      Strong verbal and written English communication skills


Interested candidates please send CV to Prof Wentong Cai at



About Modelling and Simulation Group at NTU


The Modelling and Simulation (M&S) group led by Prof Wentong Cai has been conducting impactful research in M&S over two decades.  The group has published extensively in top venues in the area such as ACM TOMACS, SMPT (Elsevier), IEEE TPDS, FGCS (Elsevier), JPDC (Elsevier), and ACM SIGSIM PADS and has won 12 Best Paper Awards in international conferences.  Recent ones include IEEE/ACM DS-RT’18, ACM SIGSIM PADS’18, and ACM SIGSIM PADS’17.  Many alumni of the group now work as Professors in leading universities in Europe and China or Research Engineers in leading IT companies world-wide such as Microsoft, Alibaba, Tencent, and Huawei.  


The research of the group mainly focuses on the intersection between Computer Science and M&S.  The current research interests include: performance and scalability of discrete event simulation, large-scale distributed virtual environment and cloud gaming, dynamic data-driven agent-based modelling and simulation, and agent-based simulation applications (e.g., crowd and traffic simulation). 



About The Project –

Optimising Emergency Medical Systems Using 3D Modelling and Simulation of Built Public Spaces – The EMS3D Project


The EMS3D project aims to save lives and improve quality of life for victims of mass casualty incidents, and acute medical events such as cardiac arrest and heart attack, by developing a powerful set of tools that utilise Virtual Singapore (VS) assets to optimise emergency medical responses. These will complement and build on (i) existing service planning efforts that use discrete event modelling to determine placement of ambulance bases and guide land transport via the road network; (ii) current planning activities for disaster response and evacuation from the new Singapore General Hospital; and (iii) a current initiative around upgrading and placement of Automated External Defibrillators (AEDs) at a major housing estate in Singapore.


Figure 1 shows an overview of the EMS3D project. The tools developed in EMS3D will address the built infrastructure, including what happens after emergency crews arrive at the scene of a public space, where currently available 2D mapping software (including navigation software such as Google Maps) have large gaps, and the actual response depends critically on internal architecture and crowd behaviour. Based on cardiac events alone, we anticipate that by reducing the ‘last mile’ emergency response time, survival rate can be improved.


Figure 1: Overview of the EMS3D Project


Using agent-based models, our objective is to develop and test tools that optimise EMS preparation and operations, enabling better facility and service planning, personnel training and real-time guidance. By incorporating crowd-behaviour modelling, we will target these three use cases: i) `last-mile’ emergency medical service (EMS) provision; ii) evacuation of emergency department (ED); and iii) AED placement optimization (see Figure 2).


Figure 2: Use Cases of the EMS3D Project


This is a multi-disciplinary project.  Other key investigators involved in the project are: Prof Peter Sloot (NTU & UvA), Prof Michael Lees (UvA, The Netherlands), Dr. Marcus Ong (SGH, Singapore), and Prof Russell Gruen (ANU, Australia). 



About Our Work on Agent-based Crowd Modelling and Simulation


In our previous projects, we have investigated and developed a tool for crowd modelling and simulation. A generic framework for human behavioural modelling in crowd simulation has been developed, aiming to model how humans make decisions in real-life time critical situations.  Particularly, the framework takes into account how an agent’s decision making process is affected by experiences and other people’s behaviour. This can be used to model the behaviour responses of the civilians and casualties towards the incident and the actions of the medical teams. More information about our work on agent-based crowd modeling and simulation can be found here.