Research Fellow / Engineer, Physics-Informed Neural Network
As a University of Applied Learning, SIT works closely with industry in our research pursuits. Our research staff will have the opportunity to be equipped with applied research skill sets that are relevant to industry demands while working on research projects in SIT. The primary responsibility of this role is to work on a physics-informed neural network (PINN) solution for efficient prediction of conjugate heat transfer applications. In this project, you will be part of the research team to develop a library written in Python to allow future users to apply the PINN solution for real conjugate heat transfer problems.
- Participate in and manage the research project with Principal Investigator (PI), Co-PI and the research team members to ensure all project deliverables are met.
- Meeting the project deliverables within the project timeframe, which consists of the following responsibilities:
- Designing and programming the PINN algorithm in python specifically targeted at conjugate heat transfer application
- Design and perform experiment, including selecting and rigging up sensor network, to accelerate PINN solution
- Perform computational fluid dynamics (CFD) runs for validation of PINN solution
- Improve efficiency of the PINN algorithm
- Assists in co-supervision of Final Year Projects (FYP) or capstone projects students together with the project PI
- Assists PI in drafting of reports, conference proceedings and journal articles based on the outcome of the projects
- Prepares and shares fortnightly report of results from project work with PI
- Support and coordinate procurement and maintenance of the software/hardware under the charge of the PI
- Carry out Risk Assessment, and ensure compliance with Work, Safety and Health Regulations.
- Work independently, as well as within a team, to ensure proper operation and maintenance of equipment.
- Have relevant competence in the python programming, internet of things (IoT) setup, sensors integration, python programming
- Familiar with data analytics software and platforms like JupyterLab, SciPy ecosystem, scikit-learn libraries, tensorflow libraries.
- Knowledge in Computational Fluid Dynamics, ability to use OpenFOAM is a bonus
- A good Bachelor, Masters or Ph.D degree in Data Science or Computer Engineering or Electrical Engineering from a reputable university.
- Fluent verbal and written communications.
- Good self-discipline and motivated to deliver
- Show strong initiative and take ownership of work
- Able to build and maintain strong working relationships with people within and external to the university.
- Self-directed learner who believes in continuous learning and development
- Proficient in technical writing and presentation
- Possess strong analytical and critical thinking skills