Industrial Water AI Engineer — Surrogate Modeling Lead, Singapore

In this role, you will develop and integrate software-based AI/ML surrogate modelling solutions for industrial water consumption and wastewater treatment applications, supporting sustainability goals such as improved water recycling and reduced operational carbon intensity. You will model complex physical systems potentially including fluid dynamics, heat transfer, and process equipment via simulation platforms and/or physics-enabled AI approaches to optimize industrial operations and further develop capabilities for the A*STAR Water Efficiency and Effectiveness Monitoring and Analytics System (WE2MAS).

The role requires a strong foundation in process engineering and data-driven methods, with an understanding of manufacturing and industrial systems. You will also evaluate state of the art technologies and design end-to-end workflows that bridge data to high-fidelity simulations with scalable AI surrogate models for real-world validation, deployment, and implementation at industrial sites.

• Lead and support capability development in process simulation and surrogate modeling aligned with the technical roadmap for industrial water and wastewater sustainability initiatives.
• Collaborate across teams to incorporate simulation-driven insights and surrogate models into broader digital twin to explore optimization strategies.
• Evaluate and integrate cutting-edge research in physics-based modeling and AI-driven emulation into practical, industry-ready workflows.

• Design and train machine learning models that emulate or approximate complex physical simulations, enabling faster predictive analysis.
• Apply data-driven techniques to extract key patterns and relationships from simulation and experimental datasets.
• Develop interpretable and robust surrogate models suitable for use in process design, optimization, and control applications.

• Design and implement end-to-end workflows that integrate process simulation, data extraction, feature engineering, ML model development, validation and deployment.
• Collaborate with IT and data engineering teams to integrate models with existing data infrastructure for maintainable MLOps workflows for lifecycle management.

• Collect, preprocess, and analyze datasets from simulations, experiments, and industrial systems.
• Evaluate the sensitivity and performance of process parameters through simulation and surrogate-based studies.
• Work closely with domain experts to validate correlations, surrogate model predictions and quantify model uncertainty.

• Communicate findings, methodologies, and recommendations effectively to technical and non-technical stakeholders.
• Collaborate with process engineers, plant operators, and R&D teams to ensure alignment with process improvement objectives.
• Prepare reports, technical documentation, simulation validation summaries, and deployment guides.
• Contribute to secondary roles for the team, Group, Organisation and A*STAR.

Bachelors/Masters in Mechanical, Chemical, or Industrial Engineering, Data Science, or a related field with focus on process modeling or data analytics.

• At least 2 years of experience in process simulation or the application of AI/ML to engineering problems (Preferred experience working with water quality related data/processes).
• Proven experience in developing and deploying surrogate models or applying data analytics insights into data-driven decision making tools.

Strong programming and data science skills (Python, MATLAB, TensorFlow, PyTorch, Scikit-learn).

Familiarity with surrogate modeling techniques and ML/AI workflows.

Effective communication skills to present complex modeling, simulation and data analytics insights to non-technical audiences.