"Senior Research Staff & Post-doctoral Fellow, Research Staff in Planning and Scheduling of Automated Material Handling Systems"

We are seeking highly motivated researchers to join our project on “Planning and Scheduling of Automated Material Handling Systems in Semiconductor Manufacturing Environments.” This project is carried out in collaboration with leading semiconductor companies and targets real-world, industrially relevant challenges. Our goal is to advance cutting-edge research while ensuring strong practical applicability. The research will concentrate on three interrelated areas:

• a) Semiconductor Equipment Scheduling: In semiconductor fabs, a vast number of wafers are processed across hundreds or even thousands of manufacturing tools following highly complex workflows. We aim to develop optimization models and algorithms to improve wafer processing sequences across semiconductor manufacturing tools, with the objectives of reducing cycle times and lowering work-in-progress (WIP) inventory, thereby increasing throughput and overall manufacturing efficiency.
• b) Automated Material Handling System (AMHS) Scheduling: In modern semiconductor fabs, AMHS, typically realized through Overhead Hoist Transport (OHT), is responsible for transferring wafers between manufacturing tools. Given the massive production scale, the AMHS must handle tens of thousands of transports requests every day, ensuring timely and reliable delivery of wafers to the correct tools. Our research seeks to develop efficient and adaptive scheduling algorithms for AMHS systems to significantly reduce transport delays, improve material flow, and enhance coordination between logistics and manufacturing processes.
• c) Digital Twin System: We aim to construct a digital twin framework that integrates real-time data and simulation models to mirror the physical manufacturing and logistics systems. This enables performance monitoring, predictive analysis, and the evaluation of scheduling strategies in a virtual environment, thereby supporting more robust and adaptive decision-making in semiconductor manufacturing.

Responsibilities:

• a) To address the above challenges, applicants are expected to formulate mathematical models of the problems and develop efficient solution methods, particularly by leveraging techniques from machine learning and operations research.
• b) The applicants are expected to deliver research outcomes to our industry partners, to support practical applications in semiconductor manufacturing.
• c) The applicants are expected to write and submit high-quality academic papers.

Qualifications

• a) Education: Ph.D. in Automation, Industrial Engineering, Systems Engineering, Computer Science, or a closely related field.
• b) Technical Skills: Strong programming proficiency is required.
• c) Research Experience: Relevant research experience in related problem domains, or research experience in scheduling, routing, and multi-agent pathfinding (MAPF) algorithms – Experience across multiple areas is a strong plus; Experience developing ML-based optimization approaches is a strong plus; A strong publication track record is highly desirable.
• d) Industry collaboration experience: Prior experience in collaborative R&D with industry partners is a strong plus.

Application: Send your CV, a cover letter, and the contact information of three referees to Dr. Anbang Liu (anbang@hku.hk) and cc to Prof. Lin (shaoclin@hku.hk). The complete reference letters should be submitted as soon as possible after the application.