EngD position: AI for Underground Infrastructure Detection and Characterisation

Utwentecareers; Netherlands; Remote; EUR 36,000 - 42,000; Full time

Benefits offered by this job

Pension

Health care benefits

Holiday allowance 8%

Year-end bonus 8.3%

Job summary

University of Twente invites applications for a two-year EngD position focusing on developing AI models to detect underground infrastructure in GPR radargrams and estimate depth. The project leverages datasets from UT FieldLab and involves collaboration with industry partners under ZoARG programme.

The role requires a Master’s degree in a related field, ML experience, and Python proficiency. The position offers a gross monthly salary of €3173, with standard Dutch pension and health benefits and

Qualifications

• Master’s degree or equivalent in Civil Engineering, Geomatics, Computer Science, Data Science, or related field.
• Experience with machine learning, data analytics, or computer vision techniques.
• Programming experience in Python and familiarity with ML frameworks such as PyTorch or TensorFlow.

Responsibilities

• Analyze existing GPR interpretation methods and ML techniques.
• Explore AI approaches for automated utility characterization.
• Prepare and manage large GPR datasets collected at the UT FieldLab.
• Design, train, and validate ML models for GPR interpretation.
• Compare developed models with literature and commercial software.
• Collaborate with academic and industrial partners.

Skills

ML techniques

Python

Geospatial data

Data analytics

Communication

Education

Master’s degree or equivalent

Tools

PyTorch

TensorFlow

Job description

Job description

In this EngD project, you will develop an AI model that automatically detects underground infrastructure in GPR radargrams and estimates its depth. The project builds on the growing availability of high-quality GPR data collected at the University of Twente’s Utility Mapping Site (UMS), a unique test environment for utility mapping technologies.

Current machine learning models and their training data are limited in size, comprehensiveness, and realism – resulting in partial automation with limited performance. This constrains their usefulness in real-world conditions. Your challenge is to develop and validate machine learning models using systematically collected and accurately annotated GPR datasets. By combining geospatial data, subsurface sensing, and AI, you will contribute to the next generation of utility mapping technologies and support safer excavation practices.

Your environment

This project is part of the ZoARG|ReDUCE programme, a collaborative initiative aimed at minimizing excavation damage to underground infrastructure in the Netherlands. You will work within a multidisciplinary environment that includes:

• The University of Twente’s Departments of Civil Engineering and Management (CEM) and Applied Earth Sciences (AES)
• The Utility Mapping Site (UMS) at the UT FieldLab
• Industry collaborators involved in the ZoARG programme

What you will do

• Analyse existing GPR interpretation methods, machine learning techniques, and relevant software tools
• Explore and evaluate AI approaches for automated utility characterization
• Prepare, preprocess, and manage large GPR datasets collected at the Utility Mapping Site
• Design, develop, train, and validate machine learning models for interpreting GPR radargrams
• Compare developed models with existing approaches reported in literature and commercial software solutions
• Work in close partnership with infrastructure owners, contractors, technology providers, and researchers engaged in the ZoARG programme
• Report findings and translate results into practical recommendations for measurement practice and technology evaluation

Your profile

• A Master’s degree or equivalent experience in Civil Engineering, Geomatics, Computer Science, Data Science, or a related field
• Experience with machine learning, data analytics, or computer vision techniques
• Programming experience in Python and familiarity with machine learning frameworks such as PyTorch, TensorFlow, or similar tools
• Curiosity about geospatial data, remote sensing, subsurface sensing, or utility mapping applications;
• Strong analytical and problem-solving skills
• The ability to work independently and collaborate effectively with academic and industrial partners
• Excellent communication skills and proficiency in English

Our offer

• Two-year full-time EngD position, where scientific and research domains are combined optimally with education and practical implementation of innovative design
• Full status as an employee at the UT, including pension and health care benefits
• A tailor‑made post‑master build programme that has an educational component (40%) as well as a design project (60%)
• A gross monthly salary of €3173
• An annual holiday allowance of 8% of the gross annual salary, and an annual year‑end bonus of 8.3%
• Minimum of 29 holidays per year in case of full‑time employment
• A work environment on a green and lively campus with (free access) to sports and leisure facilities
• Mentorship that supports your professional and personal growth
• Upon finishing the programme, you will be awarded a certified degree. You can use the academic title EngD and register as a Technological Designer in the Dutch registry of the Royal Institution of Engineers in the Netherlands (KIVI).

Information and application

Submit your application by 27 November 2026. Your application must include:

A recent CV detailing relevant academic and (if applicable) professional experience

A motivation letter (max. 1.5 pages) explaining your interest and relevant background for this project

An overview of your MSc degree: including thesis title, abstract, and grade list

For questions about the project or your eligibility, please contact the selection committee at: [e-mail] or [e-mail].

Selected candidates will be invited for an (online) interview with the academic supervisors. Interviews will take place on 11 and 18 December.

Starting date of this position is in the first half of 2027.

Preferred candidates will proceed to a matching interview with the project steering committee.

Screening is part of the procedure.

About the organisation

At the Faculty of Engineering Technology (ET), we work on engineering for impact: developing smart, sustainable, human-centred and technological solutions for societal challenges. We connect fundamental education, research and practice across five core domains: Asset & Maintenance engineering, Intelligent Manufacturing Systems, Personalised Health Technology, Resilience Engineering, and Sustainable Production, Energy and Resources.

We work on education and research in mechanical engineering, civil engineering and industrial design engineering. Together, we learn by making, creating, and innovating, addressing challenges in a solution‑oriented way. Quality, connection and inclusivity are the foundation of our culture.

In our open community, students, researchers and staff collaborate with industrial and societal partners. This enables us to develop insights, applications and solutions that add value to society.

A Master’s degree or equivalent experience in Civil Engineering, Geomatics, Computer Science, Data Science, or a related field Experience with machine learning, data analytics, or computer vision techniques Programming experience in Python and familiarity with machine learning frameworks such as PyTorch, TensorFlow, or similar tools Curiosity about geospatial data, remote sensing, subsurface sensing, or utility mapping applications; Strong analytical and problem-solving skills The ability to work independently and collaborate effectively with academic and industrial partners Excellent communication skills and proficiency in English