Research Assistant

Interested applicants are invited to apply directly at the NUS Career Portal Your application will be processed only if you apply via NUS Career Portal We regret that only shortlisted candidates will be notified Job Description The Community Assets and Activity Chain Modelling (CA-ACM) project is a research study commissioned by the Health Promotion Board to investigate how Singapore's built environment shapes residents' daily activities and lifestyle patterns. The project aims to identify features of the built environment that make active living intuitive and natural; develop composite indicators to measure and rank the attractiveness of different urban settings for various population groups; and uncover how these environmental features influence the type of physical activities people choose to engage in. The project brings together experts in urban studies, data science, public health, and social science research to surface evidence-based insights and design strategies that promote more active living We are seeking a highly motivated Research Assistant to contribute to the machine learning and geospatial modelling components of the CA-ACM project Responsibilities: Prototype and implement ML algorithms and quantitative models, with a focus on activity and mobility sequences Independently develop, test, and iterate model structures, taking initiative to translate urban behavioural theory into data-driven logic Clean, label, and visualize spatiotemporal mobility and built environment data with GIS tools (e.g., QGIS, GeoPandas, PostGIS)Collaborate with an interdisciplinary team to co-design and build up a framework for resident archetyping, incorporating dimensions including lifestyle, physical activity, and environmental exposure Develop software for data driven archetyping, using object-oriented programming to model archetype classes and attributes for downstream simulation Apply unsupervised learning and rule-based methods to classify movement, demographic and health data Develop and evaluate behavioural response models in simulations to test how archetypes respond to interventions Conduct behavioural simulations and visualize outputs through maps, dashboards, and policy-facing summaries Prepare academic outputs, including abstracts, posters, reports, and journal manuscripts Present research findings to both academic and applied audiences and actively contribute feedback to the broader research team Qualifications Master's degree Computer Science, Data Science, Urban Analytics, Geoinformatics, Geography or a related field Proficiency in Python and ML libraries (e.g., scikit-learn, XGBoost, PyTorch or TensorFlow)Skillset: STATS/probs/applied math, coding and prototyping, prior experience working with sequence data (trip chains) is high plus/population data is a plus, attention to details Experience with temporal or spatial behavior modeling is preferred Understanding of sequence modeling or spatial ML methods is a plus Strong background and expertise in one or more of the following areas: spatiotemporal data analysis, activity chain or mobility modeling, machine learning for urban applications, geospatial analysis using GIS tools, or urban informatics Experience working in interdisciplinary research teams and collaborating across diverse fields Strong quantitative or qualitative research skills Excellent written and verbal communication skills Excellent interpersonal skills Highly motivated, independent and able to work in a dynamic environment Application Procedure: Interested applicants should submit a dossier consisting of the following: a cover letter (maximum 3 pages)up-to-date CV a statement describing their research trajectory, interests and career ambitions contact details for three referees (only short-listed applicants will be invited to submit reference letters)The anticipated start date for the position is 31 December 2025. We will begin evaluating candidates immediately, but the position will remain open until a suitable candidate is found. Further enquiries should be sent to #J-18808-Ljbffr