Interested applicants are invited to apply directly at the NUS Career Portal. Please note your application will only be processed if you apply via NUS Career Portal.
NUS Career Portal link: https://careers.nus.edu.sg/job/Research-Fellow-%28Supply-Chain-Management%29/32507-en_GB/
We regret that only shortlisted candidates will be notified.
Job Role/ Core Capabilities
- Experience with logistics and supply chain processes, including transport operations, fleet management, and operational readiness frameworks
- Model & Algorithm Development: Design, build and implement optimisation models for various transportation contexts, and machine learning classifiers
- Heuristics & Solvers: Develop and refine custom heuristics and metaheuristics (e.g., Tabu Search, Genetic Algorithms) to find high-quality solutions for large-scale, real-world problems. Utilise commercial and open-source solvers (e.g., Gurobi, CPLEX, Google OR-Tools).
- Formulate and solve Mixed-Integer Linear Programmes (MILP) for real-time vehicle-task assignment including objective function design and constraint modelling
- Design, implementation, and delivery of simulation data science solutions to perform system-of-systems discrete event simulations for significantly complex operational processes (e.g., AnyLogic, AnyLogistix, FlexSim, Arena, Demo 3D, etc.)
- Data Analysis & Feature Engineering: Analyse historical and real-time data from multi-source inputs
- Experience analysing large datasets and applying data-cleaning techniques along with performing statistical analyses leading to the understanding of the structure of datasets
- Machine Learning & AI: Train, evaluate, and deploy supervised classification models (e.g., XGBoost, LightGBM), design ensemble pipelines combining rule-based, probabilistic, and ML components apply explainability tools (e.g., SHAP, LIME) to produce interpretable, auditable decision outputs
- Experience with data visualisation and visualisation tools (e.g., MS Power BI, Tableau), including design and delivery of operational KPI dashboards covering driver-task mismatch rates, fleet health distribution, fatigue heatmaps, and dispatch allocation efficiency
Requirements
Education
- PhD in industrial engineering, Operations Research, Computer Science, Operations Research or an equivalent field
Experience
- Min 1-2 years of experience in logistics and supply chain management
- Experience in research or applied engineering environment delivering optimisation, simulation, or decision-support systems for operational contexts
- Track record of end-to-end model delivery: problem formulation: data pipeline, algorithm design, implementation, validation, stakeholder communication
Technical Skills
- Experience or familiarity with optimisation packages such as Gurobi, CPLEX, OR-Tools, and Python PuLP for MILP formulation and solver configuration
- Experience or familiarity with simulation tools such as AnyLogic, AnyLogistix, FlexSim, Arena, AIMMS, Demo 3D or similar tools
- Proficiency in Python including pandas, numpy, scipy, scikit-learn, XGBoost, PuLP/OR-Tools, and pytest proficiency in SQL for data queries and operational log extraction
- Experience with MS Power BI, Tableau
- Familiarity with MLflow or equivalent experiment tracking tools for ML retraining pipelines
- Proficiency in MS Office
