Dries Benoit
Just added
just-published
PhD Position in Explainable Machine Learning for Manufacturability Prediction at Ghent University Ghent University in Belgium
Degree Level
PhD
Field of study
Computer Science
Funding
Available
Deadline
Apr 5, 2026
Country
Belgium
University
Ghent University

How do Chinese students apply for this?
Sign in for free to reveal details, requirements, and source links.
Where to contact
Official Email
Keywords
About this position
Ghent University invites applications for a full-time PhD position in the Department of Marketing, Innovation and Organisation, within the CVAMO Flanders Make Lab. This doctoral fellowship focuses on developing advanced machine learning models to predict manufacturability and manufacturing effort directly from CAD geometry. The research aims to translate geometric design information into quantitative estimates of manufacturing effort and cost, leveraging state-of-the-art methods such as Graph Neural Networks, geometric deep learning, and multi-view learning architectures. A strong emphasis is placed on explainable AI, enabling the identification of geometric features that drive cost increases or infeasibility, and providing interpretable managerial decision support.
The successful candidate will enroll as a full-time PhD student for four years (subject to yearly positive evaluations) under the supervision of Professor Dries Benoit. The position includes opportunities to contribute to teaching activities (Data Mining, Machine Learning) and collaborative industry projects, each up to 10% of the appointment. The research environment is highly stimulating, with close connections to industrial applications and opportunities for conference participation, doctoral school training, and international publication.
Applicants must hold or be about to complete a Master’s degree in a relevant field (e.g., business engineering, industrial engineering, mathematics, engineering, computer science, artificial intelligence). Strong study results, a keen interest in machine learning and AI, background knowledge in neural networks and deep learning, strong analytical and programming skills, and excellent English proficiency are required. The ability to work independently and collaboratively is essential.
The fellowship offers a competitive stipend (100% of the net salary of an AAP member, tax-free, amount based on family status and seniority) for up to 48 months, with various staff benefits including training opportunities, holiday leave, bicycle allowance, and eco vouchers. The targeted starting date is September 1, 2026.
To apply, submit a motivation letter, detailed CV with study results, and copies of your degree and transcripts (all in PDF format) via email to [email protected] by April 5, 2026, 23:59. Please ensure the subject line of your email starts with “PHD26”. Ghent University is committed to equal opportunities and diversity; all qualified candidates are encouraged to apply.
Funding details
Available
What's required
Applicants must hold or be about to complete a Master’s degree (MA or MSc) in a relevant field such as business engineering, industrial engineering, mathematics, engineering, computer science, or artificial intelligence. Strong study results are an asset. Candidates should have a strong interest in scientific research in machine learning and AI, preferably with background knowledge in neural networks and deep learning. Strong analytical and programming skills, clear scientific and communicative skills (critical thinking, scientific writing, presentation skills), and a profound knowledge of English are required. Ability to work independently and in a collaborative research environment is expected.
How to apply
Submit your application by April 5, 2026, 23:59 via email to [email protected]. Include a motivation letter, detailed CV with study results, and copies of your degree and transcripts, all in PDF format. Ensure the email subject line starts with “PHD26”.
Ask ApplyKite AI
Professors

How do Chinese students apply for this?
Sign in for free to reveal details, requirements, and source links.