PhD Position AI Alignment: Value Assessment for Open Models & AI Systems

Job description

AI alignment refers to the goal of making AI systems behave in line with human intentions and values. AI alignment ensures that advanced AI systems operate safely and strictly within the bounds of human intentions, ethical standards, and the prevalent legal frameworks. With the rapid proliferation of AI systems, frontier LLMs, multimodal models, autonomous agents and their growing capability, there are equal risks of misalignment with human, organizational, and societal values through behavioral drift, hallucination, and adversarial exploitation. Validating models is crucial before decisions can be made about implementation and is important for continuous monitoring of systems in use, and for facilitating effective human oversight of AI. This is particularly important in high-stakes environments like law enforcement. The main challenge is that validation needs to happen simultaneously along a range of different values that are important in a law enforcement context: accuracy, but also fairness, reliability, trustworthiness, and more need to be ensured. How can we translate abstract democratic, organisational, and societal values such as algorithmic fairness, transparency, explainability (XAI) into rigorous, quantifiable engineering metrics without sacrificing the general utility of said models and AI systems?

As a PhD student at TU Delft, you will conduct impactful research on two key aspects in advancing the responsible use of AI within the Netherlands Police force. First, you will investigate the standards and values surrounding AI usage, particularly in the context of publicly available models. This entails defining what criteria these models must meet, beyond common considerations like bias and fairness. Second, you will also design methods to systematically evaluate various models against these established standards and values. This contributes to the responsible deployment of AI within policing in the Netherlands, pushes forward our understanding of how to align AI models in practice, and maximizes the efficiency of utilizing publicly available models.

1. Formalizing Value Taxonomies and Alignment Metrics

You will investigate the ethical, legal, and operational guardrails required for deploying open-weights foundation models in sensitive public-facing domains. Moving beyond superficial bias benchmarks, you will conduct deep-dive case studies within the Netherlands Police to map operational requirements to formal alignment criteria. You will define what constructs such as "trustworthiness" and "fairness" mean mathematically and procedurally when applied to complex law enforcement workflows.

2. Engineering (Automated) and Human-in-the-Loop Evaluation and Red-Teaming Pipelines

You will design and implement scalable methodologies to systematically stress-test, audit, and benchmark AI models against your established criteria. This includes exploring red-teaming methods, synthetic data generation for vulnerability probing, and investigating how downstream alignment techniques (e.g., DPO, RLHF, or constitutional AI) can be customized to enforce strict adherence to organizational values.

Your project is part of the Model-Driven Decisions Lab, a Netherlands Police - TU Delft initiative, where you will join an interdisciplinary community of four fellow PhD students who have already been hired. Together, you will share knowledge to tackle AI-assisted decision-making from different perspectives. To foster close collaboration with the stakeholders and work on practical implementation, you will spend 20% of your time at the Netherlands Police’s strategy and innovation division. Given the ethical and moral facets of your research, you will also work closely with colleagues of the Delft Digital Ethics Centre at the Faculty of Technology, Policy, and Management (TPM). Your home base will be the Web Information Systems research group at the Computer Science faculty (EEMCS). As an internationally diverse team of driven academics and students, we cultivate a welcoming and collaborative environment. We will give you all the support and training you need to evolve both personally and professionally. Learn more about your project at the Model-Driven Decisions Lab.

Job requirements

• You hold an MSc in computer science, data science, or another relevant subject such as ethics of AI, with practical machine learning/artificial intelligence courses and relevant project and thesis experience.
• You have a keen interest in AI alignment, human-AI interaction, and explainable AI, and enjoy collaborating with experts in different disciplines.
• You thrive on conducting research geared to real-world applications in the security domain and are intrinsically motivated to collaborate with the Netherlands Police.
• You harness your communication skills to work with different scientific and nonscientific stakeholders in different work cultures.

You have a good command of written and spoken English, as you will be working in an international environment. Since you will be working with the Netherlands Police, one of our pre-requisites for a suitable candidate is to have a good command of the Dutch language. This is a strong requirement due to the context of the project that will need interactions with stakeholders and data in the Dutch language.

TU Delft (Delft University of Technology)
Working at TU Delft means contributing to solutions that really make a difference.

For over 180 years, we have been training engineers who make an impact worldwide in companies, government bodies, or as entrepreneurs. Our alumni turn knowledge into concrete solutions for the challenges of today and tomorrow.

These challenges are changing rapidly. That is why we focus on themes such as energy, climate, digitalisation, artificial intelligence (AI), and smart mobility every day. Our education and research are directly aligned with what society needs now and in the future.

At TU Delft, our people make the difference. With their knowledge and curiosity, our staff provide a high-quality education and conduct pioneering research that extends beyond the campus. You will have the opportunity to take the initiative, work with others, and grow as a professional.

Working at TU Delft means join an international community of professionals and students. Together, we create knowledge, innovations, and solutions that help move the world forward.

Faculty of 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.

Click here to go to the website of the Faculty of Electrical Engineering, Mathematics and Computer Science.

PhD Position AI Alignment: Value Assessment for Open Models & AI Systems

Job description

AI alignment refers to the goal of making AI systems behave in line with human intentions and values. AI alignment ensures that advanced AI systems operate safely and strictly within the bounds of human intentions, ethical standards, and the prevalent legal frameworks. With the rapid proliferation of AI systems, frontier LLMs, multimodal models, autonomous agents and their growing capability, there are equal risks of misalignment with human, organizational, and societal values through behavioral drift, hallucination, and adversarial exploitation. Validating models is crucial before decisions can be made about implementation and is important for continuous monitoring of systems in use, and for facilitating effective human oversight of AI. This is particularly important in high-stakes environments like law enforcement. The main challenge is that validation needs to happen simultaneously along a range of different values that are important in a law enforcement context: accuracy, but also fairness, reliability, trustworthiness, and more need to be ensured. How can we translate abstract democratic, organisational, and societal values such as algorithmic fairness, transparency, explainability (XAI) into rigorous, quantifiable engineering metrics without sacrificing the general utility of said models and AI systems?

As a PhD student at TU Delft, you will conduct impactful research on two key aspects in advancing the responsible use of AI within the Netherlands Police force. First, you will investigate the standards and values surrounding AI usage, particularly in the context of publicly available models. This entails defining what criteria these models must meet, beyond common considerations like bias and fairness. Second, you will also design methods to systematically evaluate various models against these established standards and values. This contributes to the responsible deployment of AI within policing in the Netherlands, pushes forward our understanding of how to align AI models in practice, and maximizes the efficiency of utilizing publicly available models.

1. Formalizing Value Taxonomies and Alignment Metrics

You will investigate the ethical, legal, and operational guardrails required for deploying open-weights foundation models in sensitive public-facing domains. Moving beyond superficial bias benchmarks, you will conduct deep-dive case studies within the Netherlands Police to map operational requirements to formal alignment criteria. You will define what constructs such as "trustworthiness" and "fairness" mean mathematically and procedurally when applied to complex law enforcement workflows.

2. Engineering (Automated) and Human-in-the-Loop Evaluation and Red-Teaming Pipelines

You will design and implement scalable methodologies to systematically stress-test, audit, and benchmark AI models against your established criteria. This includes exploring red-teaming methods, synthetic data generation for vulnerability probing, and investigating how downstream alignment techniques (e.g., DPO, RLHF, or constitutional AI) can be customized to enforce strict adherence to organizational values.

Your project is part of the Model-Driven Decisions Lab, a Netherlands Police - TU Delft initiative, where you will join an interdisciplinary community of four fellow PhD students who have already been hired. Together, you will share knowledge to tackle AI-assisted decision-making from different perspectives. To foster close collaboration with the stakeholders and work on practical implementation, you will spend 20% of your time at the Netherlands Police’s strategy and innovation division. Given the ethical and moral facets of your research, you will also work closely with colleagues of the Delft Digital Ethics Centre at the Faculty of Technology, Policy, and Management (TPM). Your home base will be the Web Information Systems research group at the Computer Science faculty (EEMCS). As an internationally diverse team of driven academics and students, we cultivate a welcoming and collaborative environment. We will give you all the support and training you need to evolve both personally and professionally. Learn more about your project at the Model-Driven Decisions Lab.

Job requirements

• You hold an MSc in computer science, data science, or another relevant subject such as ethics of AI, with practical machine learning/artificial intelligence courses and relevant project and thesis experience.
• You have a keen interest in AI alignment, human-AI interaction, and explainable AI, and enjoy collaborating with experts in different disciplines.
• You thrive on conducting research geared to real-world applications in the security domain and are intrinsically motivated to collaborate with the Netherlands Police.
• You harness your communication skills to work with different scientific and nonscientific stakeholders in different work cultures.

You have a good command of written and spoken English, as you will be working in an international environment. Since you will be working with the Netherlands Police, one of our pre-requisites for a suitable candidate is to have a good command of the Dutch language. This is a strong requirement due to the context of the project that will need interactions with stakeholders and data in the Dutch language.

TU Delft (Delft University of Technology)
Working at TU Delft means contributing to solutions that really make a difference.

For over 180 years, we have been training engineers who make an impact worldwide in companies, government bodies, or as entrepreneurs. Our alumni turn knowledge into concrete solutions for the challenges of today and tomorrow.

These challenges are changing rapidly. That is why we focus on themes such as energy, climate, digitalisation, artificial intelligence (AI), and smart mobility every day. Our education and research are directly aligned with what society needs now and in the future.

At TU Delft, our people make the difference. With their knowledge and curiosity, our staff provide a high-quality education and conduct pioneering research that extends beyond the campus. You will have the opportunity to take the initiative, work with others, and grow as a professional.

Working at TU Delft means join an international community of professionals and students. Together, we create knowledge, innovations, and solutions that help move the world forward.

Faculty of 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.

Click here to go to the website of the Faculty of Electrical Engineering, Mathematics and Computer Science.

PhD Position Experimental Physics Thermal-Hydraulics in Advanced Nuclear Reactor Technology

Perform experimental research and develop accurate datasets that help shape the next generation of micro nuclear reactors for land-based and maritime applications. At TU Delft, you will design and operate unique thermo-hydraulic experiments that directly contribute to the safety and deployment of advanced reactor technology. You will work in an interdisciplinary consortium while collaborating closely with a second PhD researcher focused on reactor modelling and safety analysis.

Job description
TU Delft is part of a consortium led by Allseas that is developing a micro High-Temperature Reactor (HTR), being a pebble-bed design, for land-based and maritime applications. Within this project, you will generate experimental data that support reactor safety assessment and model validation.

As a PhD candidate, you will investigate passive heat removal and reactor behavior during water ingress scenarios in the MARLIN pebble-bed reactor concept. You will design, build and operate a non-nuclear experimental facility consisting of a tiltable reactor vessel with heated pebbles and advanced measurement systems.

You will perform experiments that vary pebble power, vessel orientation, water flow and pebble configurations to study heat transfer, natural convection, boiling phenomena and hotspot formation. Experiments will include extreme maritime conditions with vessel inclinations up to 90 degrees.

A second research line focuses on the influence of ship motions such as roll, pitch and heave on pebble-bed behavior. You will develop dedicated experimental setups to measure pebble movement, collision dynamics and local density variations under non-stationary conditions.

The validated datasets you generate will directly support the adjoining PhD project on high-fidelity reactor modelling and safety analysis. Together, both positions contribute to the safe deployment of advanced microreactors.

You will join TU Delft’s nuclear engineering community and have access to state-of-the-art laboratory facilities, international collaborators and doctoral education programmes. The position offers opportunities to develop expertise in thermal hydraulics, experimental methods, reactor safety and nuclear energy technologies.

Job requirements

• You hold, or will soon obtain, a Master's degree in applied physics, mechanical engineering or a related field.
• You have a strong interest in experimental research and laboratory work.
• You have a proven interest/background in thermal hydraulics (fluid dynamics and heat transfer).
• You enjoy designing, building and operating experimental facilities.
• You can work collaboratively in multidisciplinary research teams.
• You communicate effectively in spoken and written English.
• You work proactively, accurately and in a structured manner.
• You are interested in advanced nuclear energy systems and reactor safety.  

TU Delft (Delft University of Technology)
Working at TU Delft means contributing to solutions that really make a difference.

For over 180 years, we have been training engineers who make an impact worldwide in companies, government bodies, or as entrepreneurs. Our alumni turn knowledge into concrete solutions for the challenges of today and tomorrow.

These challenges are changing rapidly. That is why we focus on themes such as energy, climate, digitalisation, artificial intelligence (AI), and smart mobility every day. Our education and research are directly aligned with what society needs now and in the future.

At TU Delft, our people make the difference. With their knowledge and curiosity, our staff provide a high-quality education and conduct pioneering research that extends beyond the campus. You will have the opportunity to take the initiative, work with others, and grow as a professional.

Working at TU Delft means join an international community of professionals and students. Together, we create knowledge, innovations, and solutions that help move the world forward.

Faculty Applied Sciences
With more than 1,100 employees, including 150 pioneering principal investigators, as well as a population of about 3,600 passionate students, the Faculty of Applied Sciences is an inspiring scientific ecosystem. Focusing on key enabling technologies, such as quantum- and nanotechnology, photonics, biotechnology, synthetic biology and materials for energy storage and conversion, our faculty aims to provide solutions to important problems of the 21st century. To that end, we educate innovative students in broad Bachelor's and specialist Master's programmes with a strong research component. Our scientists conduct ground-breaking fundamental and applied research in the fields of Life and Health Science & Technology, Nanoscience, Chemical Engineering, Radiation Science & Technology, and Engineering Physics. We are also training the next generation of high school teachers.

Click here to go to the website of the Faculty of Applied Sciences.

PhD Position Distribution Systems Flexible Operation under Uncertain and Incomplete Information

Job description

The Delft University of Technology is hiring a doctoral candidate on the subject "Distribution systems flexible operation under uncertain and incomplete information". The Ph.D. position is part of the Future Network Services (FNS) Project.

The energy transition is transforming the way distribution systems at the low-voltage (LV) level are operated. Expectations are that the integration of distributed energy resources (DERs), also known as flexible assets, will continue to grow. DERs such as PVs, electric vehicles, and electric heat pumps, complemented by smart buildings, will unlock the required energy flexibility at the LV level to address technical issues such as voltage problems and network congestion. The way the flexibility provided by DERs and smart buildings can be exploited (e.g., via local flexibility markets) is still in development with many unresolved challenges. Two of these challenges revolve around data availability and operational uncertainty.

This PhD research project aims to investigate how distribution systems can exploit the flexibility of DERs and smart buildings, given limited data availability and increased operational uncertainty. Data availability is limited due to a lack of digitalization or privacy issues, while large uncertainties govern the operation of distribution systems because DERs (e.g., PV and EVs) are weather- and human behaviour-dependent. This PhD aims to address research questions such as how can AI and ML models support the coordinated operation of DERs and smart buildings in the context of limited data? How can AI and ML models increase distribution systems observability via surrogate models.

This is a four-year doctoral appointment. You will be jointly supervised by Dr. Pedro P. Vergara (Associate Professor) and Prof. Peter Palensky (Chair IEPG). You will be a member of the section Intelligent Electrical Power Grids in the Faculty of Electrical Engineering, Mathematics, and Computer Science. The project will offer opportunities to collaborate with industrial partners but also with academics from other disciplines, as required (mathematics, operations research). Within the team, we strive to develop methods that are mathematically rigorous and have near-term application potential. We are strong supporters of open science (publishing, source code, data). You will also be expected to assist in teaching activities (student supervision, labs) related to your subject area.

About the Future Network Services (FNS) Project

This PhD research is part of the Future Network Services (FNS) 6G Project, led by TNO. The FNS Project aims, among others, to deliver the innovations needed to enable real-time services for the electricity infrastructure via 6G technologies.

About the ESE Department

The research in the Department of Electrical Sustainable Energy is inspired by the technical, scientific, and societal challenges originating from the transition towards a more sustainable society and focuses on four areas:

• DC Systems, Energy Conversion and Storage (DCE&S)
• Photovoltaic Materials and Devices (PVMD)
• High Voltage Technologies (HVT)
• Intelligent Electrical Power Grids (IEPG)

The Electrical Sustainable Energy Department provides expertise in each of these areas throughout the entire energy system chain. The department owns a large ESP laboratory assembling High Voltage testing, DC Grids testing environment, and large RTDS that is actively used for real-time simulation of future electrical power systems, AC and DC protection and wide-area monitoring and protection.

The Intelligent Electrical Power Grid (IEPG) group, headed by Professor Peter Palensky, works on the future of our power system. The goal is to generate, transmit and use electrical energy in a highly reliable, efficient, stable, clean, affordable, and safe way. IEPG integrates new power technologies and smart controls, which interact with other systems and allow for more distributed and variable generation.

Job requirements
Essentials:

• Basic knowledge of power systems.
• Completed an MSc degree in a highly technical related discipline (computer science, electrical engineering, etc.) and you were at the top of your class.
• Excellent analytical skills and a solid basis in machine learning and/or operational research. You can understand literature in both disciplines.
• Excellent oral and written communication skills in English proven by a minimum score of 100 in TOEFL or IELTS of 7.0 per sub-skill (writing, reading, listening, speaking). Candidates do not need to present the test results as part of their application. These results will be requested at a later stage during the selection procedure. For more information see https://www.tudelft.nl/onderwijs/opleidingen/phd/admission
• You enjoy performing research. You are independent, self-motivated and eager to learn.
• You are keen to work with partners to link real-world challenges to fundamental research questions.

Desirables:

• Knowledge of electrical distribution systems, power flow, and congestion management.
• Experience with optimization methods and scheduling problems as well as optimization packages such as Pyomo.
• You enjoy programming and have experience with Python, machine learning, command-line tools, version control.

TU Delft (Delft University of Technology)
Working at TU Delft means contributing to solutions that really make a difference.

For over 180 years, we have been training engineers who make an impact worldwide in companies, government bodies, or as entrepreneurs. Our alumni turn knowledge into concrete solutions for the challenges of today and tomorrow.

These challenges are changing rapidly. That is why we focus on themes such as energy, climate, digitalisation, artificial intelligence (AI), and smart mobility every day. Our education and research are directly aligned with what society needs now and in the future.

At TU Delft, our people make the difference. With their knowledge and curiosity, our staff provide a high-quality education and conduct pioneering research that extends beyond the campus. You will have the opportunity to take the initiative, work with others, and grow as a professional.

Working at TU Delft means join an international community of professionals and students. Together, we create knowledge, innovations, and solutions that help move the world forward.

Faculty of 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.

Click here to go to the website of the Faculty of Electrical Engineering, Mathematics and Computer Science.

PhD Position Experimental Physics Thermal-Hydraulics in Advanced Nuclear Reactor Technology

Perform experimental research and develop accurate datasets that help shape the next generation of micro nuclear reactors for land-based and maritime applications. At TU Delft, you will design and operate unique thermo-hydraulic experiments that directly contribute to the safety and deployment of advanced reactor technology. You will work in an interdisciplinary consortium while collaborating closely with a second PhD researcher focused on reactor modelling and safety analysis.

Job description
TU Delft is part of a consortium led by Allseas that is developing a micro High-Temperature Reactor (HTR), being a pebble-bed design, for land-based and maritime applications. Within this project, you will generate experimental data that support reactor safety assessment and model validation.

As a PhD candidate, you will investigate passive heat removal and reactor behavior during water ingress scenarios in the MARLIN pebble-bed reactor concept. You will design, build and operate a non-nuclear experimental facility consisting of a tiltable reactor vessel with heated pebbles and advanced measurement systems.

You will perform experiments that vary pebble power, vessel orientation, water flow and pebble configurations to study heat transfer, natural convection, boiling phenomena and hotspot formation. Experiments will include extreme maritime conditions with vessel inclinations up to 90 degrees.

A second research line focuses on the influence of ship motions such as roll, pitch and heave on pebble-bed behavior. You will develop dedicated experimental setups to measure pebble movement, collision dynamics and local density variations under non-stationary conditions.

The validated datasets you generate will directly support the adjoining PhD project on high-fidelity reactor modelling and safety analysis. Together, both positions contribute to the safe deployment of advanced microreactors.

You will join TU Delft’s nuclear engineering community and have access to state-of-the-art laboratory facilities, international collaborators and doctoral education programmes. The position offers opportunities to develop expertise in thermal hydraulics, experimental methods, reactor safety and nuclear energy technologies.

Job requirements

• You hold, or will soon obtain, a Master's degree in applied physics, mechanical engineering or a related field.
• You have a strong interest in experimental research and laboratory work.
• You have a proven interest/background in thermal hydraulics (fluid dynamics and heat transfer).
• You enjoy designing, building and operating experimental facilities.
• You can work collaboratively in multidisciplinary research teams.
• You communicate effectively in spoken and written English.
• You work proactively, accurately and in a structured manner.
• You are interested in advanced nuclear energy systems and reactor safety.  

TU Delft (Delft University of Technology)
Working at TU Delft means contributing to solutions that really make a difference.

For over 180 years, we have been training engineers who make an impact worldwide in companies, government bodies, or as entrepreneurs. Our alumni turn knowledge into concrete solutions for the challenges of today and tomorrow.

These challenges are changing rapidly. That is why we focus on themes such as energy, climate, digitalisation, artificial intelligence (AI), and smart mobility every day. Our education and research are directly aligned with what society needs now and in the future.

At TU Delft, our people make the difference. With their knowledge and curiosity, our staff provide a high-quality education and conduct pioneering research that extends beyond the campus. You will have the opportunity to take the initiative, work with others, and grow as a professional.

Working at TU Delft means join an international community of professionals and students. Together, we create knowledge, innovations, and solutions that help move the world forward.

Faculty Applied Sciences
With more than 1,100 employees, including 150 pioneering principal investigators, as well as a population of about 3,600 passionate students, the Faculty of Applied Sciences is an inspiring scientific ecosystem. Focusing on key enabling technologies, such as quantum- and nanotechnology, photonics, biotechnology, synthetic biology and materials for energy storage and conversion, our faculty aims to provide solutions to important problems of the 21st century. To that end, we educate innovative students in broad Bachelor's and specialist Master's programmes with a strong research component. Our scientists conduct ground-breaking fundamental and applied research in the fields of Life and Health Science & Technology, Nanoscience, Chemical Engineering, Radiation Science & Technology, and Engineering Physics. We are also training the next generation of high school teachers.

Click here to go to the website of the Faculty of Applied Sciences.