Postdoctoral Researcher in Automated Metadata Generation for Data Reuse

Descrizione

Testo originale dell'annuncio (in inglese)

Do you have passion for FAIR and open data, and a drive to improve the data landscape? Do you enjoy solving both technical and societal challenges? The Intelligent Data Engineering lab (INDElab) is looking for a postdoc in the BridgeMD project. Join Us! We are looking for a postdoctoral researcher who can help us develop technology to help researchers identify and reuse useful datasets across different domains. Data reuse across domains is hindered by insufficient or poorly tailored metadata and documentation. As a result, datasets often remain underutilized, despite their potential value across diverse research communities. In this project, you will address this challenge by leveraging recent advances in Generative AI to reduce the distance between data providers and data reusers. Specifically, you will develop methods capable of automatically generating tailored metadata and associated documentation for defined user groups, integrated into widely used open-source data repository software platforms. The resulting system will be able to produce outputs such as domain-specific vocabulary mappings, example code to facilitate data reuse, and contextualized descriptions that reflect the concepts and methods familiar to the target research community. BridgeMD aims to make datasets produced in one domain significantly more reusable across scientific fields and beyond; for students, policy makers, and other societal stakeholders. By harnessing state-of-the-art AI for metadata generation, it enhances the value of existing data, supports ongoing investments in FAIR implementation, and strengthens the foundations for future data-driven and AI-supported research in natural and engineering sciences. This is what you will do To fulfil the goals of the BridgeMD project, and the responsibilities of a postdoctoral researcher, we expect you to take on the following: conducting independent research in on data reuse and metadata, resulting in academic publications in peer-reviewed international conferences or journals; collaborate with our research engineer to develop open-source software integrations for data reuse; developing a systematic evaluation protocol; organising events and other collaborations with community partners for testing and dissemination; supervising Bachelor and Master thesis projects. What we ask of you We are looking for someone who is passionate about open science, and excited to work with a diverse set of stakeholders on designing a generalizable solution. You should also have: a recent PhD in Computer Science or Engineering, Information Studies, Human-Technology Interaction or similar; experience with user studies, preferably qualitative methods such as interviews, think-alouds or focus groups; significant coding experience in Python; experience with LLMs, in particular as part of agentic systems (e.g. use of OpenRouter, vLLM). Experience training LLMs and deep learning in general is a plus; good communication skills in oral and written English. Contributions to OpenML or other dissemination platforms are a plus. An understanding of the metadata data ecosystem and open standards for research data are appreciated. This is what we offer you A temporary contract for 38 hours per week for the duration of 2 years with a probationary period of two months (the initial contract will be for a period of 12 months and after satisfactory evaluation it will be extended by 12 month for a total duration of 2 years). The preferred starting date is November 1st. The gross monthly salary, based on 38 hours per week and dependent on relevant experience, ranges between € 3,706 to € 5,760 (scale 10). This does not include 8% holiday allowance and 8,3% year-end allowance. The UFO profile Researcher is applicable. A favourable tax agreement, the ‘30% ruling’, may apply to non-Dutch applicants. The Collective Labour Agreement of Universities of the Netherlands is applicable. Curious about our extensive secondary benefits package? You can read m