Intern - Digital Automation & Solutions Team

Job Overview

Join an inclusive team passionate about using their expertise in the relentless pursuit of innovation for customers and partners. The solutions we build help make everything from virtual reality experiences to breakthroughs in neural networks possible, while committing to integrity, sustainability, and giving back to our communities.

Location, Department, and Project

• Location: Singapore
• Department: Digital Automation & Solutions Team
• Project Title: Dynamic Batch Delivery Scheduling System for Autonomous Mobile Robot Fleet Operations

Project Description

Micron’s Fab 10 facility uses a fleet of Autonomous Mobile Robots to complete internal parts-delivery requests across the site. Currently, warehouse technicians determine whether multiple delivery requests should be grouped into a single robot mission or released individually, based on factors such as delivery priority, destination proximity, robot availability, and estimated return timing.

This project focuses on developing a dynamic scheduling system that evaluates the full queue of pending delivery requests in real time. The system will determine whether a request should be grouped with other compatible requests, released immediately to the next available robot, or held briefly for a returning robot. The goal is to improve delivery scheduling decisions and reduce overall fleet-wide delivery time through data-driven optimization.

Objective

Design, develop, and validate a dynamic scheduling model that improves Autonomous Mobile Robot fleet utilization, reduces delivery waiting time, and enables more consistent decision-making for internal parts delivery.

Project Scope

• Study the current manual dispatching and delivery grouping process.
• Identify relevant data inputs, operational constraints, and decision factors.
• Formulate the scheduling and delivery grouping problem into an optimization model.
• Develop and test a real-time scheduling algorithm.
• Compare algorithm performance against current dispatching outcomes.
• Document the methodology, results, and recommendations for future implementation.

Learning Opportunities

• Gain exposure to smart manufacturing and warehouse automation in a semiconductor environment.
• Apply optimization, scheduling, routing, and data analysis concepts to a real business problem.
• Learn how Autonomous Mobile Robot fleet operations are planned and evaluated.
• Develop practical experience in modelling, algorithm development, simulation, and performance benchmarking.
• Build stakeholder communication skills through project reviews and final presentation.
• Gain exposure to Artificial Intelligence-enabled workflows, Generative Artificial Intelligence, Code Assist tools, and Large Language Models where relevant to research, analysis, documentation, and solution development.

Deliverables

• Current-state process and constraint analysis.
• Optimization model for dynamic delivery scheduling and request grouping.
• Prototype scheduling algorithm.
• Performance comparison against current dispatching outcomes.
• Final report with methodology, findings, results, and recommendations.
• Final presentation to stakeholders.

Impact

This project is expected to improve the efficiency of Autonomous Mobile Robot fleet operations by enabling more consistent scheduling decisions, reducing delivery waiting time, and improving robot utilization. It may also provide a foundation for future automation, optimization, and smart manufacturing enhancements within internal logistics operations.

Skillsets Required

• Foundation in optimization, operations research, scheduling, routing, or combinatorial optimization.
• Programming knowledge for modelling and analysis, preferably Python.
• Strong analytical and problem-solving skills.
• Ability to work with data, process flows, and operational constraints.
• Good communication and documentation skills.
• Familiarity with optimization solvers such as Gurobi or Google Operations Research Tools is preferred.
• Familiarity with simulation, data analytics, Artificial Intelligence-enabled workflows, Generative Artificial Intelligence, Code Assist tools, or Large Language Models is preferred, where relevant to the project.

Course of Interest

The ideal candidate should be pursuing Industrial Engineering, Systems Engineering, Mechanical Engineering, Computer Engineering, Computer Science, Data Science, Operations Research, Supply Chain Engineering, or a related course of study.

Internship Duration

The ideal candidate should be able to commit to an internship period of 5 months.

Opportunities for Full-Time Employment

Successful completion of the internship may provide the candidate with opportunities to be considered for future full-time employment, subject to business needs and individual performance.