🇳🇱 Amsterdam, Netherlands · 10h ago
Postdoctoral Researcher – LLMs for AI-Assisted Educational Support
Vrije Universiteit Amsterdam (VU Amsterdam)
LinkedInEnglish-friendly
Your functionAs a Postdoctoral Researcher, you will play a central role in the development of Large Language Model (LLM) components that support education professionals in creating, maintaining and improving Individual Development Perspective Plans (Ontwikkelingsperspectiefplannen; OPPs).The project does not aim to automate the creation of complete OPPs. Instead, you will investigate how LLMs can best support education professionals with specific, well-defined subtasks within the OPP workflow. Examples include generating a first draft of the Integrative Student Profile (Integratief Beeld) based on already completed OPP sections, supporting the formulation of the Educational Perspective / justification of the expected educational pathway, and providing targeted feedback on the quality of existing OPP text.A key research challenge is to determine how information from different OPP sections (e.g., support needs) can be represented and provided to an LLM so that the generated output is coherent, concrete, actionable and consistent with the underlying information. You will develop and evaluate prompting strategies, structured input representations and, where useful, fine-tuned models for these tasks.You will also work on LLM-based quality feedback. A quality rubric developed in the first phase of the project defines criteria such as concreteness, actionability, coherence, specificity of support needs and quality of the integrative profile. You will investigate how LLMs can use these criteria to identify weaknesses in OPP text and provide concise, prioritized and practically useful suggestions for improvement.An equally important part of the position concerns the interaction between the AI component and the education professional. The AI system should support professional judgement rather than replace it. You will therefore investigate questions such as: When should AI support be offered? What information should be shown to the user? How should generated text and feedback be presented? How can users easily accept, reject or adapt suggestions? And how can the system make clear which OPP information was used to generate a suggestion?Together with the software development partner, you will help design how these AI components can be integrated into an existing student information system. This includes defining the information exchanged between the student information system and the LLM, designing modular API-based components, and contributing to user-interface concepts that allow education professionals to invoke AI support within their normal workflow.The research will be conducted iteratively and in close collaboration with education professionals. Prototype components will first be evaluated independently for output quality and will subsequently be integrated into the Presentis student information system (leerlingvolgsysteem) for user-centred evaluation and refinement.To get a better idea about the project, see: https://www.ru.nl/onderzoek/onderzoeksprojecten/opp-vullen-en-onderhouden-met-ai (https://www.ru.nl/onderzoek/onderzoeksprojecten/opp-vullen-en-onderhouden-met-ai)Your dutiesselect and benchmark state-of-the-art open-source and commercial LLMs for Dutch-language OPP-related tasksdevelop and evaluate LLM components for generating specific OPP sections, initially focusing on the Integrative Student Profile and the Educational Perspective / justification of educational pathwaydevelop prompting strategies and structured input representations that combine information from relevant OPP sectionsinvestigate when prompt engineering is sufficient and when techniques such as fine-tuning or retrieval-augmented generation provide added valuedevelop rubric-based LLM methods for detecting quality issues in existing OPP text and generating concise, prioritized improvement suggestionsdevelop methods for identifying generic or baseline support that occurs repeatedly across OPPs and distinguish this from student-specific support needsdesign and evaluate human-AI interaction patterns for AI-assisted OPP writing and revisioninvestigate how generated text and feedback can best be presented so that education professionals retain control over the final contentcollaborate with software developers who will develop the technical architecture and API-based integration of LLM components into the Presentis student information systemdefine which OPP data elements should be transferred to an LLM component and how generated output should be returned and incorporated into the existing workflowevaluate LLM output using the OPP quality rubric developed in the project and through evaluation with education professionalsconduct co-design and user studies with teachers, behavioural scientists, support coordinators and other education professionalsanalyze the quality, reliability and limitations of generated OPP text and AI feedbackcontribute to open-source implementations of reusable OPP-specific LLM components and evaluation toolspublish results in peer-reviewed AI, NLP, Human-AI Interaction and/or Educational Technology venuessupervise MSc students working on related research topicscollaborate closely with project partners from education, research and software developmentYour profileWe are looking for a motivated researcher with expertise in modern Natural Language Processing and Large Language Models, who enjoys translating cutting-edge AI research into practical educational applications.Job RequirementsPhD in Artificial Intelligence, Computer Science, Computational Linguistics, Natural Language Processing, Human-AI Interaction, Data Science or a closely related fieldability to work in a multidisciplinary consortium involving researchers, software developers and education professionalsexcellent communication skills in English; proficiency in Dutch, or the willingness and ability to develop sufficient Dutch proficiency to work with Dutch-language educational materials and users, is strongly preferredaffinity with education, special education or educational technology is highly desirabledemonstrated hands-on experience with Large Language Models and modern NLP methodsgood programming skills, preferably in Python, and experience with relevant ML/NLP frameworks such as PyTorch and Hugging Face Transformersexperience with prompt engineering and systematic evaluation of generative AI systemsability to design and run empirical comparisons between different models, prompting strategies and system configurations.experience with qualitative and/or quantitative evaluation of generated textinterest in Human-AI Interaction and in designing AI systems that support rather than replace professional decision-makingexperience with Retrieval-Augmented Generation, model fine-tuning, structured generation, LLM evaluation frameworks or human-centred AI is an advantageexperience with co-design, user studies or iterative prototyping with domain professionals is an advantage.analytical and scientific writing skillsWe offer the opportunity to work on a socially relevant AI project in close collaboration with schools, software developers and educational experts. The position provides ample opportunity to publish internationally while contributing directly to AI applications that can improve educational practice.As a university, we strive for equal opportunities for all, recognising that diversity takes many forms. We believe that diversity in all its complexity is invaluable for the quality of our teaching, research and service. We are always looking for talent with diverse backgrounds and experiences. This also means that we are committed to creating an inclusive community so that we can use diversity as an asset.We realise that each individual brings a unique set of skills, expertise and mindset. Therefore we are happy to invite anyone who recognises themselves in the profile to apply, even if you do not meet all the requirements.What do we offer?EducationA challenging position in a socially engaged organisaSourced from LinkedIn. Relocantly aggregates public job postings; apply on the original site.