AI-Enhanced Optimization for Manufacturing and Transportation Systems

Format: On Campus
Number of Interns: 3
Duration: 6–8 weeks (July/August)
Start Date: June 29, 2026
End Date: July 31, 2026
Application Deadline: May 1, 2026
Project Supervisor: Assistant Professor Milad Elyasi
Project Description: This research internship focuses on developing advanced optimization and machine learning solutions for real-world problems arising in manufacturing, transportation, and logistics systems. The project blends mathematical optimization with machine learning to design intelligent decision-making tools. Students will work on topics inspired by current research, including:

• vehicle routing problem,
• machine scheduling problem,
• metaheuristics for large-scale combinatorial problems,
• integrating ML components into optimization models.

The goal is to explore how optimization + AI can jointly enhance efficiency, robustness, and adaptability of modern industrial systems.

Project Tasks:

• Analyze real-world or simulated datasets from manufacturing, logistics, or transportation systems.
• Formulate optimization models for scheduling, routing, or resource allocation.
• Develop and test metaheuristic algorithms (ALNS, VNS, GA) for large-scale solution search.
• Integrate machine learning into optimization pipelines.
• Validate proposed methods using benchmark instances or synthetic data.
• Prepare documentation, final reports, and a research presentation at the end of the internship.

Requirements:

• Undergraduate student in Industrial Engineering, Manufacturing Engineering, Computer Science, Data Science, or related fields.
• Completed at least 180 ECTS (senior standing).
• GPA > 2.7. • Basic knowledge of optimization algorithms, mathematical modeling, or machine learning.
• Proficiency in Python (NumPy, Pandas, preferably Pyomo/Gurobi).
• Interest in solving real-world analytical problems.

This internship offers an interdisciplinary research experience combining operations research, machine learning, and data-driven decision-making. Interns will gain hands-on experience with modeling, algorithm design, and computational experiments—directly aligned with modern research directions in manufacturing and transportation optimization.

Click for Google Form.