About the role
AI summarisedThe role is for a Scientist in Computational Sustainability at A*STAR's Institute of High Performance Computing, focusing on computational fluid dynamics research for urban sustainability, marine decarbonisation, and renewable energy. The scientist will develop advanced simulation capabilities, physics-informed machine learning models, and surrogate models, collaborating with multidisciplinary teams and industry partners.
ResearchFull-time
Key Responsibilities
- Developing advanced modelling and simulation capabilities for multi-physics, multi-component, and multi-phase fluid flow problems.
- Designing and implementing Physics-Informed Machine Learning (PIML) models, including core methodologies for embedding governing physical principles into machine learning frameworks.
- Developing physics-based, data-driven surrogate models and data assimilation techniques for flow-related problems and applications.
- Working closely with multidisciplinary teams to develop and apply CFD codes across diverse application areas, such as environmental flows, hydrodynamics, turbulent flows, and dispersion modelling.
- Collaborating with industry partners, affiliated research institutes, and other key stakeholders to translate research outcomes into real-world impact.
Requirements
- A strong academic background in physics and/or engineering, preferably with a PhD in Mechanical, Aerospace, Civil, Environmental, Chemical, Computational Engineering, Applied Physics, or a closely related discipline.
- Solid understanding of core physics and engineering principles, including fluid dynamics, transport phenomena, and thermodynamics, with demonstrated expertise in multi-phase and multi-component flows.
- In-depth knowledge of numerical methods for fluid flow simulations (e.g. finite volume methods, lattice Boltzmann methods, volume-of-fluid techniques) and experience with high-performance computing.
- Experience in developing computational methods, including the use and customization of open-source CFD codes (e.g. OpenFOAM, Nek5000, Palabos); familiarity with optimization techniques (e.g. linear, nonlinear, and real-time optimization) is an advantage.
- Proficiency in programming languages such as Python, C/C++, Fortran, CUDA, and/or Julia.
- Experience with machine learning techniques, including neural networks and deep learning, is highly desirable.
- Strong interpersonal and communication skills, with the ability to work effectively both independently and as part of a multidisciplinary team; excellent command of written and spoken English; self-motivated, resourceful, and committed to high standards of professional integrity.