Job Description

We are seeking a highly motivated Research Assistant to support a funded research project on cost-effective, wireless, occupant-centric control strategies for whole-building energy retrofit. The project focuses on integrating data-driven methods and large language models (LLMs) with building performance data to enable scalable, occupant-aware control strategies for existing buildings. The role emphasizes AI-enabled analysis, model development, and decision support, rather than traditional rule-based control design. The Research Assistant will be supervised by Dr. Adrian Chong, Department of the Built Environment, College of Design and Engineering, National University of Singapore.

•    Design and evaluate occupant-centric control strategies for energy-efficient building retrofit using data-driven and AI-enabled approaches.
•    Develop and fine-tune large language model (LLM)-based workflows to support interpretation of building operation data and control decision-making.
•    Conduct systematic validation of proposed methods using simulation results, measured building data, or benchmark datasets.
•    Perform quantitative analysis of energy, comfort, and operational performance under different control and retrofit scenarios.
•    Support the development of reproducible modelling and analysis pipelines, including documentation and version control.
•    Contribute to the preparation of technical reports and peer-reviewed publications, including method description, validation, and discussion of limitations.
•    Collaborate with interdisciplinary researchers to integrate building performance knowledge with AI and control methodologies.
•    Perform other duties as assigned.

Job Requirements

Qualifications and Skills:

•    Bachelor’s and Master’s degree in Architecture, Architecture Engineering, Mechanical Engineering, or a related field
•    Demonstrated proficiency in Python for data analysis and model development
•    Experience working with large language models (LLMs), including prompt engineering, fine tuning, and integration of LLMs into decision-support workflows
•    Familiarity with building energy management systems
•    Good written and verbal communication skills 

More Information

Location: Kent Ridge Campus

Organization: College of Design and Engineering

Department : The Built Environment

Employee Referral Eligible: No

Job requisition ID : 31475