Research Fellow (Smart & Green Navigation)

National University of Singapore; Singapore; On-site; SGD 80,000 - 110,000; Full time

Job summary

The National University of Singapore invites applications for a Research Fellow to advance autonomous vessel control algorithms and energy-efficient navigation. You will work within a multi-disciplinary engineering team on data-driven modelling for low-emission shipping and contribute to publications and industry collaborations.

The role requires a PhD in a quantitative field and a strong background in autonomous systems, optimization, control theory, and data analytics, with programming

Qualifications

• PhD required in a quantitative discipline with strong research background.
• Proven ability in autonomous systems, optimization, control theory and data analytics.
• Proficiency in Python/MATLAB/R/Excel for data analysis and modelling.
• Familiarity with maritime data (AIS, IMO COLREGS) and decarbonization concepts is a strong plus.

Responsibilities

• Develop and validate autonomous vessel control algorithms for robust performance in dynamic environments.
• Develop and validate dynamic path-planning and guidance algorithms for autonomous ships.
• Build and calibrate models to estimate fuel consumption and emissions for vessels.
• Assess impact of autonomous controls on fuel and carbon emissions for international shipping.
• Collaborate with team on data collection, modelling and publications.

Skills

Autonomous systems

Optimization modelling

Control theory

Data analytics

Machine learning

Uncertainty modelling

Education

PhD in Industrial Engineering, Marine Engineering, OR, Energy Systems or related quantitative discipline

Tools

Python

MATLAB

R

Excel

Job description

Company description

The National University of Singapore is the national research university of Singapore. Founded in 1905 as the Straits Settlements and the Federated Malay States Government Medical School, NUS is the oldest higher education institution in Singapore

Job description

The Centre for Maritime Studies at the National University of Singapore (NUS) invites applications for the position of Research Fellow to support the development of innovative algorithms for the safe and energy-efficient navigation of autonomous ships, alongside advanced ship emission modeling. The Research Fellow will be part of a multi-disciplinary engineering team developing autonomous control algorithms that enable safe, efficient, and low-emission navigation of vessels, to lay groundwork for applications in international shipping.

Key Responsibilities

• Develop and validate autonomous vessel control algorithms that optimize vessel behaviour in dynamic environmental conditions using stochastic and robust methods.
• Develop and validate dynamic path-planning and guidance algorithms for MASS.
• Build and calibrate models to estimate fuel consumption and emissions for vessels.
• Assess the impact of autonomous control measures on fuel consumption and carbon emissions, especially in the context of international decarbonization goals.
• Contribute to publications and reports, and collaborate with the research team in data collection, modelling and analysis.

Preferred Qualifications

• PhD in Industrial Engineering, Marine Engineering, Operations Research, Energy Systems, or a related quantitative discipline.
• Strong background in: autonomous systems, optimization modelling, control theory, data analytics and machine learning, uncertainty modelling.
• Proficiency in programming (Python/MATLAB/R/Excel) for data analysis and modelling.
• Familiarity with international maritime regulation (e.g. IMO COLREGS), maritime datasets (e.g., AIS, IHS, SeaWeb), vessel characteristics, or decarbonization technologies and measures is a strong plus.
• Strong publication record, analytical skills, and ability to communicate with both academic and industry audiences.
• Ability to work independently and collaboratively in a multi-disciplinary environment.
• (Preferred) Knowledge of Singapore/Asia maritime ecosystem and related industry datasets.