JOB DESCRIPTION

We are seeking a highly motivated PhD candidate to join our research team focused on Collaborative Metadata Management for Large Data Repositories supporting data-driven methods and AI models in plant science. The project is part of the CropXR program, a highly collaborative 10-year national initiative of universities and industry, with a mission to grow resilient crops developed by a data-driven design.
This PhD project will analyse and address the requirements for establishing effective metadata management in large data repositories. The expected outcomes are innovative technical solutions, systems, and methodologies for metadata elicitation, metadata evolution, and metadata quality management.
The goal of these outcomes is to improve the practices of metadata management in plant sciences in accordance with the FAIR principles (Findable, Accessible, Interoperable, Reusable). This will enable our team of interdisciplinary partners to reliably develop, train and deploy complex AI models for improving plant resilience (e.g., plants which are more resilient to temperature changes or drought).

Key Challenges

• The challenges of large-scale collaborative metadata management for supporting plant sciences are not yet well understood. This PhD project requires an inquisitive mind and an enthusiastic communicator eager to explore this new frontier!
• We anticipate challenges related to effective and efficient elicitation of metadata. As providing metadata is often not prioritized or enjoyed by many academics and practitioners, novel innovative solutions are needed to address this issue. Such solutions can be found in various fields, for example by fostering stronger and more effective communities and social workflows around metadata (inspired by comparable communities in software development as found on e.g., GitHub or Stack Overflow), or by developing AI-assisted tools and workflows which can guide and support users more effectively.
• User Modelling is essential. While this project innovates in the field of data management and information management, also many human-centric issues like incentivisation and communication will be encountered. Thus, technical solutions need to keep both algorithmic challenges and human aspects in mind!
• Item Modelling is a plus. We deal specifically with metadata for plant sciences. Background knowledge (or the willingness to familiarize yourself with such background knowledge) in relevant related plant science fields is beneficial.

Your Role

• You will develop technical solutions, systems, and algorithms processing and handling metadata, but you will also perform quantitative and qualitative research on the requirements and effectiveness of such solutions.
• With your work, you will contribute to interdisciplinary research integrating data-driven mechanistic models and machine learning models into plant sciences with the goal to develop more resilient breeds.
• Given the interdisciplinarity and dynamic environment inherent to this project, this project requires that you adapt and adjust your solutions to the specifications and needs of practitioners in the field.

Benefits

• Opportunity to work on cutting-edge interdisciplinary research with significant real-world impact.
• Collaborative and dynamic research environment which is highly interdisciplinary and international.
• Collaborate with researchers, practitioners, and developers within various disciplines.
• Support for professional development and attendance at international conferences.

This PhD position is positioned within the Web Information System Group, part of the Computer Science department of the Delft University of Technology. The PhD position will be supervised by Dr. Christoph Lofi. The PhD project will be done in close collaboration with our partner institutions in the CropXR project.

JOB REQUIREMENTS

• A Master’s degree in Computer Science, Artificial Intelligence (AI), or Bioinformatics, with an affinity to data management, information management, and/or data science.
• Strong analytical and problem-solving skills.
• Strong interpersonal communication and collaboration abilities.
• Experience with biological data integration or computational biology is a plus, but not required. However, enthusiasm for learning about computational biology is expected!
• Excellent programming skills and familiarity with databases, data repositories, and data lakes.
• Experience or enthusiasm for developing AI-driven systems utilizing Large Language Models and/or conversational agents.
• Willingness and experience to perform quantitative and qualitative user research, e.g., user studies or interviews.
• Ability to work independently as part of a multidisciplinary team. You will work within a department for Computer Science, collaborating within the CropXR project with biologists, bio-informaticians, and agriculture specialists.
• Doing a PhD at TU Delft requires English proficiency at a high level to ensure that the candidate can communicate and interact well, participate in English-taught Doctoral Education courses, and write scientific articles and a final thesis. For more details please check the Graduate Schools Admission Requirements. Dutch language skills are a plus and appreciated, but not required.

• You will develop technical solutions, systems, and algorithms processing and handling metadata, but you will also perform quantitative and qualitative research on the requirements and effectiveness of such solutions.
• With your work, you will contribute to interdisciplinary research integrating data-driven mechanistic models and machine learning models into plant sciences with the goal to develop more resilient breeds.
• Given the interdisciplinarity and dynamic environment inherent to this project, this project requires that you adapt and adjust your solutions to the specifications and needs of practitioners in the field