Data Scientist - Geospatial Analytics

Role Overview

We seek a Data Scientist specialized in geospatial analytics to collaborate with planners, analysts, and stakeholders within the Ministry of Education (MOE). The candidate will transform intricate business needs into clear analytical and technical specifications, conduct exploratory data analysis to uncover insights, and design scalable, practical solutions tailored for long-term infrastructure and space planning.

Key Responsibilities

• Work closely with MOE teams to interpret long-term planning requirements into well-defined data and machine learning specifications.
• Design comprehensive machine learning frameworks supporting geospatial and demand forecasting use cases, such as the MOE's Spatial Modelling Engine.
• Develop data pipelines, feature engineering strategies, and model deployment systems that ensure robustness, maintainability, and extensibility over multi-year horizons.
• Build, test, and deploy machine learning models alongside geospatial analytics in production environments by integrating multiple data sources including housing developments, demographics, migration trends, land-use plans, and accessibility metrics.
• Collaborate with engineering and platform teams to maintain operational models and monitor performance over time.
• Develop and refine predictive spatial models, utilizing approaches like spatial regression, time-series forecasting, agent-based modeling, and deep learning, continuously validating and improving forecast accuracy.

Candidate Requirements

• Proven practical experience in data science with demonstrable success delivering production machine learning solutions.
• Prior work with geospatial data and tools is highly desirable; experience in demographic modelling, urban planning, or public sector analytics is advantageous.
• Familiarity with Singapore's planning environment, including datasets like the URA Master Plan and HDB housing pipelines, is beneficial.
• Proficiency in Python and popular data science libraries such as scikit-learn, PyTorch, or TensorFlow.
• Experience with geospatial frameworks (GeoPandas, QGIS, PostGIS, ArcGIS) is a plus.
• Strong SQL skills and experience with cloud platforms (AWS, GCP, or Azure) are required.
• Comfortable managing the complete ML lifecycle from data preparation to model deployment and monitoring, including advanced techniques such as ensemble methods, regularization, agent-based modeling, and forecasting.
• Excellent communication skills for articulating technical insights to non-technical stakeholders and collaborating within multidisciplinary teams.