PhD Positions in Explainable and Privacy Preserving AI

AI is changing how we live and decide, yet trust remains fragile. Join PriXAI, our new VIDI-funded project, to create privacy-safe, decision-focused explanations for trustworthy AI.

Job Description

AI systems are increasingly used in high-stakes settings such as healthcare where trustworthiness is essential. Today’s explainability methods often do not provide meaningful decision support and, in some cases, can even leak sensitive training data. Models are especially unreliable and privacy-risky when they encounter inputs that were poorly represented in their training data.

Our new project PriXAI, funded through a VIDI grant, aims to solve this. The project develops techniques that identify when a model is operating in such high-risk regions and uses this information to design new, privacy-preserving learning and explanation methods. Instead of producing generic explanations, PriXAI focuses on generating targeted, privacy-safe evidence that helps users understand when predictions can be trusted.

We are offering two PhD positions that will contribute to this mission. This PhD work is important because it advances the foundations needed for AI systems that are both privacy-secure and reliable in real-world decision-making settings.

PhD Position 1: Explainability for Decision Support

You will develop explanation and evidence-generation methods that remain stable, informative, and decision-relevant even under privacy noise and limited training support. An understanding of current explainable AI techniques is highly beneficial.

PhD Position 2: Privacy Preserving Explanations

You will design methods to release model outputs and explanations under rigorously defined privacy guarantees. This includes working with techniques such as differential privacy and PAC-privacy to enable safe model and explanation release. Familiarity with privacy-preserving machine learning methods is a plus.

Both PhD candidates will work closely together as part of a joint research team headed by Dr. Megha Khosla. They will also collaborate regularly with external partners working on explainability and privacy as well as for applications in the healthcare and social-science domains.

“To thrive as a PhD candidate, it’s crucial to have a strong research mindset driven by curiosity and passion for your topic. Reflecting on your motivation for pursuing a PhD trajectory is essential, as this path involves unique challenges and uncertainties inherent to scientific exploration. Success requires dedication, adaptability, the ability to analyze complex problems, manage your time effectively, innovate and stay resilient under pressure. Combined with the ability and willingness to work independently and collaborate well, these qualities are indispensable for a fulfilling PhD journey. These experiences will build you as an independent researcher, expand your professional network, and pave the way for diverse career paths, inside or outside academia.”

Job Requirements

We are looking for motivated candidates with a Master’s in CS/AI/Data Science (or related field), strong ML foundations, and solid programming experience. Depending on the position, some background in privacy or explainability is preferred.

Doing a PhD at TU Delft requires English proficiency at a certain level to ensure that you can interact well with others, participate in English-taught Doctoral Education courses, write scientific articles and a final thesis, and share your research results with a wider audience.

TU Delft (Delft University of Technology)

Delft University of Technology is built on strong foundations. As creators of the world-famous Dutch waterworks and pioneers in biotech, TU Delft is a top international university combining science, engineering and design. It delivers world class results in education, research and innovation to address challenges in the areas of energy, climate, mobility, health and digital society. For generations, our engineers have proven to be entrepreneurial problem-solvers, both in business and in a social context.

Faculty Electrical Engineering, Mathematics and Computer Science

The Faculty of Electrical Engineering, Mathematics and Computer Science (EEMCS) brings together three scientific disciplines. Combined, they reinforce each other and are the driving force behind the technology we all use in our daily lives. Technology such as the electricity grid, which our faculty is helping to make completely sustainable and future-proof. At the same time, we are developing the chips and sensors of the future, whilst also setting the foundations for the software technologies to run on this new generation of equipment – which of course includes AI. Meanwhile we are pushing the limits of applied mathematics, for example mapping out disease processes using single cell data, and using mathematics to simulate gigantic ash plumes after a volcanic eruption. In other words: there is plenty of room at the faculty for ground-breaking research. We educate innovative engineers and have excellent labs and facilities that underline our strong international position. In total, more than 1000 employees and 4,000 students work and study in this innovative environment.

Conditions of Employment

Doctoral candidates will be offered a 4-year period of employment in principle, but in the form of 2 employment contracts. An initial 1.5 year contract with an official go/no go progress assessment within 15 months, followed by an additional contract for the remaining 2.5 years assuming everything goes well and performance requirements are met.

Salary and benefits are in accordance with the Collective Labour Agreement for Dutch Universities, increasing from €3059 - €3881 gross per month, from the first year to the fourth year based on a fulltime contract (38 hours), plus 8% holiday allowance and an end-of-year bonus of 8.3%.

As a PhD candidate you will be enrolled in the TU Delft Graduate School. The TU Delft Graduate School provides an inspiring research environment with an excellent team of supervisors, academic staff and a mentor. The Doctoral Education Programme is aimed at developing your transferable, discipline-related and research skills.

The TU Delft offers a customisable compensation package, discounts on health insurance, and a monthly work costs contribution. Flexible work schedules can be arranged.

Additional Information

For more information about this vacancy, please contact Dr. Megha Khosla, Assistant Professor in the Multimedia group at m.khosla@tudelft.nl.