PhD in Explainability and Humans in the Loop in Optimization Processes Eindhoven University of Technology in Netherlands

PhD opportunity at Eindhoven University of Technology (TU/e) in the Information Systems Group of the Department of Industrial Engineering & Innovation Sciences.

The project is titled PhD in Explainability and Humans in the Loop in Optimization Processes and sits within the EU-funded CoRDS Doctoral Network (Confident Data-Driven Decision Support), a Marie Skłodowska-Curie Actions Doctoral Network focused on data-driven optimization, trustworthy machine learning, and decision support. The research goal is to bring humans into the loop of optimization processes by using explainable AI to improve decision quality, transparency, and trust calibration.

The PhD will investigate how domain knowledge from human decision-makers can be formalized and integrated into optimization both before solving, as priors, and after solving, through structured feedback. The work package emphasis is transparency, and the project includes developing novel knowledge representation methods, human-in-the-loop optimization algorithms, and interactive tools that combine graphical and natural language interfaces for expert knowledge elicitation.

Key research themes include knowledge representation, explanation-mediated interaction, bidirectional HITL frameworks, trust calibration, user studies, expert feedback, and evaluation across multiple optimization domains and human roles. The project also aims to understand when human intervention improves results and when algorithmic outputs should be trusted more.

The successful candidate will be supervised by Dr. Isel Grau and Dr. Yingqian Zhang at TU/e. The position is based at TU/e in Eindhoven, with secondments to an industry partner for real logistics scenarios and to the University of Vienna for project collaboration.

Applicants should hold a Master’s degree in Artificial Intelligence, Computer Science, Data Science, Operations Research, Industrial Engineering, or a closely related field. Strong skills in machine learning, explainable AI, and programming are expected, along with interest or experience in optimization, human-computer interaction, cognitive decision-making, experimental evaluation, and conversational interfaces such as dialogue systems or LLM-based tools. English proficiency at C1 level is required.

The appointment is full-time for four years and includes an intermediate assessment after nine months. Salary is according to Dutch university scale P (€3,204–€4,051 gross per month), plus a year-end bonus and vacation pay. TU/e also offers training, a dynamic international environment, and standard employment benefits.

Applications are reviewed on a rolling basis and the vacancy remains open until filled. Apply online with a cover letter and CV including publications and three references.