Job Description:

TCOMS is seeking a highly motivated and technically proficient candidate to join its team in the development of a digital twin-enabled Infrastructure Health Monitoring System for Offshore and Coastal Infrastructure. The successful candidate will play a key role in the development of hybrid modeling and predictive analytics frameworks to assess infrastructure integrity and settlement, supporting proactive maintenance, early warning, and long-term resilience of marine assets.

Key Responsibilities:•

Contribute to the development of a digital twin-enabled Infrastructure Health Monitoring framework combining multi-sensor data, numerical models, and AI for marine structures.
• Apply model updating and data assimilation techniques to estimate key parameters and improve prediction accuracy.
• Build probabilistic prediction systems to assess structural health or settlement of marine structures, accounting for uncertainty in decision-making.
• Design and train machine learning / deep learning / physics-informed models to predict structural responses (e.g. dynamic responses for offshore structures, settlement behaviors for coastal protection infrastructures) using data from multiple sources, considering external factors / coastal processes, e.g. waves, wind, current, and tides.
• Validate the system through field deployment at a Proof-of-Concept site and benchmark performance.
• Collaborate closely with interdisciplinary teams to deliver impactful technical outcomes and peer-reviewed publications.

Requirements:

• PhD degree in Coastal Engineering, Ocean Engineering, Civil Engineering, Applied Mathematics, or a related discipline.

• At least 2 years of experience
• Strong foundation in coastal or ocean engineering, with knowledge of wave-structure interaction, tidal influences, and soil-water-structure response in nearshore / offshore environments.
• Proficiency in data assimilation techniques, including Bayesian inference, Kalman filtering and its variants, and model updating, with demonstrated application to engineering systems.
• Experience in developing data-driven models (machine learning, deep learning) and/or physics-informed models for structural or geospatial monitoring problems.
• Familiarity with coastal and offshore infrastructure systems, such as seawalls, breakwaters, quay walls, floating platforms, or station-keeping systems is an advantage.
• Proficiency in scientific programming using Python and/or MATLAB for data analysis, model development, and AI workflows.
• Proven ability to work both independently and collaboratively in interdisciplinary teams.

The above eligibility criteria are not exhaustive. A*STAR may include additional selection criteria based on its prevailing recruitment policies. These policies may be amended from time to time without notice. We regret that only shortlisted candidates will be notified.