Phd Position Value-based Assessment Methods for Ai Systems

2 dagen geleden


Delft, Nederland TU Delft Voltijd

**PhD Position Value-Based Assessment Methods for AI Systems**:
**Challenge**: Developing and operationalizing value-based assessment methods for AI systems.

**Change**: Driving validation of AI systems to ensure that only trustworthy models are used.

**Impact**: Enhancing police trustworthiness through AI alignment at the Dutch National Police.

**Job description**

AI alignment refers to the goal to make AI systems behave in line with human intentions and values. With the rapid proliferation of AI systems and their growing capability, there are equal risks from misalignment. Validating models is a crucial step before decisions can be made about implementation and is important for continuous monitoring of systems in use. The challenge is, however, that validation needs to happen along a range of different values that are important for AI to possess at the police: accuracy, but also fairness, reliability, trustworthiness, and more need to be ensured.

AI alignment refers to the goal of making AI systems behave in line with human intentions and values. With the rapid proliferation of AI systems and their growing capability, there are equal risks of misalignment. Validating models is crucial before decisions can be made about implementation and is important for continuous monitoring of systems in use. The challenge is, however, that validation needs to happen along a range of different values that are important for AI to possess at the police: accuracy, but also fairness, reliability, trustworthiness, and more need to be ensured.

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 concerning openly available models to begin with. This entails defining what criteria these models must meet, beyond common considerations like bias and fairness. You will research which values AI systems need to be aligned with through in-depth case studies at the Netherlands Police. Second, you will also design methods to systematically evaluate various models against these established standards and values. This contribution ensures the responsible deployment of AI within the police force, pushes forward our understanding of how to align AI models in practice, and maximizes the efficiency of utilizing publicly available models.

Through these efforts, you will significantly contribute to advancing the important area of AI alignment and help foster an ethical and accountable AI culture within the organization.

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 have a keen interest in AI alignment, human-AI interaction and explainable AI and enjoy collaborating with experts in different disciplines.
- You harness your communication skills to work with different scientific and nonscientific stakeholders in different work cultures.

**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.

Challenge. Change. Impact

**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 complete



  • Delft, Nederland TU Delft Voltijd

    PhD Position Value-Based Assessment Methods for AI Systems- **Challenge**: Developing and operationalizing value-based assessment methods for AI systems. **Change**: Driving validation of AI systems to ensure that only trustworthy models are used. **Impact**: Enhancing police trustworthiness through AI alignment at the Dutch National Police. Job...

  • Phd Position

    3 maanden geleden


    Delft, Nederland TU Delft Voltijd

    PhD position - AI DeMoS Lab- Improve our practice of democracy in the age of AI Develop AI systems for a meaningful democratic engagement. Job description TU Delft is a top tier university and is exceedingly active in the field of Artificial intelligence. AI DeMoS Lab is one of the Delft AI labs, which focuses on developing AI for democracy. The lab aims...

  • Phd Position

    6 dagen geleden


    Delft, Nederland TU Delft Voltijd

    **PhD Position - Artificial Intelligence for Reuse in the Built Environment**: **Take on the challenge of AI-driven design innovation by developing advanced computational methods to integrate reclaimed structural components into sustainable building solutions.** **Job description** The waste from building demolition presents a significant societal, economic...


  • Delft, Nederland TU Delft Voltijd

    **PhD Position AI/ML Algorithms for Next Generation Transportation Systems**: **_Are you curious how AI and ML can revolutionize the design of next-generation transportation systems?_**: **Job description** Do you aspire to conduct groundbreaking AI/ML research while collaborating closely with Amazon Science Teams? Join us and make a real-world...


  • Delft, Nederland TU Delft Voltijd

    PhD Position Embedded AI for 6G Networks- Join the Dutch 6G flagship project to help shape the future of communications! Job description 6G networks will utilise frequencies from sub 6 GHz to mmWave and THz bands, thereby substantially increasing the number as well as the heterogeneity of the required base stations. This complexity is further exacerbated...


  • Delft, Nederland TU Delft Voltijd

    Two (2) PhD Positions on Algorithms for Formal AI Verification and Explainability- Do you want to make an impact in algorithms that formally guarantee reliability of AI in deployment? When deploying AI, the real world is often different from simulations. To make AI more rigorous, we are looking for two PhD researchers to work on novel methods for verifying...


  • Delft, Nederland TU Delft Voltijd

    Two (2) PhD Positions on Algorithms for Formal AI Verification and Explainability- Teaser Do you want to make an impact in algorithms that formally guarantee reliability of AI in deployment? When deploying AI, the real world is often different from simulations. To make AI more rigorous, we are looking for two PhD researchers to work on novel methods for...


  • Delft, Nederland TU Delft Voltijd

    **PhD Position on Human Autonomy for AI Safety**: **_To automate or not to automate crisis decisions?_** In human-AI-teams, often, the distinction between tasks to be automated (or not) are made via simplified guidelines (‘humans are better at’ / ‘machines are better at’), yet not taking into account team dynamics and trust. A hallmark of control...


  • Delft, Nederland TU Delft Voltijd

    PhD Position Systems Science for Sustainable Safety- Job description At the Institute for Health Systems Science (IHSS) at the faculty of Technology, Policy and Management (TPM), a PhD position will become available dedicated to responsibility in healthcare systems in relation to safe care. The IHSS is a recently established TPM initiative that has a...


  • Delft, Nederland TU Delft Voltijd

    **PhD Position Artificial Intelligence for State Evaluation of Socio-Physical Systems**: **Job description**: Our society relies on well-functioning infrastructure systems, such as transportation, water and energy supply, and telecommunication networks. These systems are highly interdependent, and poor performance or malfunction of one or several of them can...


  • Delft, Nederland TU Delft Voltijd

    PhD Position Explainable Reinforcement Learning for Maintenance Planning under Uncertainty- Improve safety in aviation by developing explainable AI systems that optimize maintenance planning under uncertainty. Job description The goal of this PhD is to harness the power of Reinforcement Learning (RL) to enhance air transport planning under uncertainty. It...


  • Delft, Nederland TU Delft Voltijd

    PhD Position Safe Learning for Interconnected Systems- Job description The successful applicants will work on algorithms and techniques to make Safe Learning (SL) for Large Interconnected Systems a reality. This is a unique opportunity to develop and test new AI techniques for complex interconnected systems, such as those in future (6G and beyond)...


  • Delft, Nederland TU Delft Voltijd

    PhD Position Assesment Methods for Perpetual Recycling of Asphalt Concrete- **_Develop the fundamental background for perpetual recycling and sustainable future pavements._** Job description Ensuring sustainable future roads requires perpetual, effective recycling of asphalt concrete. So far, recycling in pavement engineering is practice driven and as such...


  • Delft, Nederland TU Delft Voltijd

    **PhD Position on Uncertainty in Multi-Fidelity Digital Twins for Infrastructure Management**: **Job description**: Despite significant progress in digitalizing the built environment—such as bridges, cities, and other infrastructures—there are critical factors that may limit the benefits of deploying digital twins. Digital twins require comprehensive and...


  • Delft, Nederland TU Delft Voltijd

    PhD position: Big Data Analytics and AI in Port Performance Optimization - Infrastructure Use- Job description **Research context** Ports are vital nodes in the global logistics network, facilitating international trade and commerce. They connect nations and ensure the smooth flow of imports and exports, boosting economic development. Efficient operations...


  • Delft, Nederland TU Delft Voltijd

    PhD Position Effective Metadata Management for Data-Driven Plant Resilience Enhancement- **_Join us in advancing the frontier of plant sciences and making a tangible impact on agricultural resilience through the power of machine learning!_** Job description This exciting opportunity will involve analyzing the research gaps for establishing effective...


  • Delft, Nederland TU Delft Voltijd

    PhD position Trustworthiness of Auto-Generated Systems- Job description We are seeking a motivated PhD student to work on the challenge of ensuring trustworthiness for auto-generated software. The increasing reliance on third-party software, including the use of AI agents for code, significantly enhances the efficiency of software development. However,...


  • Delft, Nederland TU Delft Voltijd

    **PhD Position Safe Control of Uncertain Systems from Data**: **_Challenge:_**_ Ensure the safety of the decisions of probabilistic systems using data_ **_Change:_**_ Develop novel control theory and machine learning methods for uncertain dynamical systems_ **_Impact: _**_Produce new intelligent, possibly data-driven, methods for safe control of...


  • Delft, Nederland TU Delft Voltijd

    **PhD Position Physics-informed Learning and Layered Control Architectures for High-tech Greenhouses**: **Job description**: High-tech greenhouses play a crucial role in ensuring sustainable, affordable, and reliable local food production. The construction and operation of high-tech greenhouses is therefore expected to grow significantly over the next...


  • Delft, Nederland TU Delft Voltijd

    PhD Position Predictive Aircraft Maintenance- **_Challenge: Predict the minimum failure time of aircraft components_** **_ Change: Use both classical data science methods and machine learning_** **_ Impact: Safe and more efficient aircraft maintenance_** Job description Imagine you are going on holidays: You take the train to the airport and enjoy a...