.png){kind=logo}
Turn global news into intelligence: build small, efficient multilingual AI models in the National Police lab AI.
Job description
News from around the world offers early signals of crime trends — from drug-trafficking hotspots to new modi operandi — but extracting the relevant entities, timelines and relations is challenging, as news sources are scattered, asynchronous, multilingual and multimodal. Furthermore, law enforcement agencies cannot afford to share sensitive data with external parties, so methods must avoid external cloud APIs and be light enough to run on limited hardware.
Your job
This 24-month postdoctoral position is a close collaboration between the National Police Lab AI (Floris Bex and Jelte Mense) and the Natural Language Processing Group (Albert Gatt) at Utrecht University. Together, we want to explore how small models can extract useful information on specific crime themes, such as drug trafficking, primarily from publicly available news sources. Relevant tasks include identifying relevant entities (who did what, where), and inferring timelines (when, and in what order) and relations (e.g. links to specific countries or groups). A promising direction is to train or fine-tune small-scale models via distillation from larger models, including through the use of synthetic data. This in turn raises interesting questions about the robustness of the resulting models, their ability to generalise, and their susceptibility to known issues related to synthetic data training, such as model collapse.
As a postdoctoral researcher on this project, you will:
- Design and evaluate methods for multimodal entity, timeline and relation extraction from multilingual news sources.
- Fine-tune and distil small-scale language models from larger models, including via synthetic data generation.
- Investigate the robustness, generalisability and limitations (e.g. model collapse) of the resulting models.
- Apply and validate the approach on real-world use cases, such as drug trafficking, together with the Netherlands police.
- Publish and present your findings at relevant conferences and in scientific journals.
Requirements
We are excited to welcome an enthusiastic new colleague who thrives in an interdisciplinary and international team and meets the following criteria:
- A PhD (obtained, or nearly completed) in Natural Language Processing or a closely related area.
- Solid knowledge of machine learning, especially deep learning.
- Experience in model development and/or fine-tuning.
- A practical mindset – interested in seeing your models used, not just published.
- Fluency in spoken and written English (C1 level). Good knowledge of Dutch is an asset, though not required, to facilitate collaboration with the Netherlands Police.
Conditions of employment
- a full-time position for 24 months;
- a permanent employment contract;
- a gross monthly salary between € 3.706 and €5.760 based on full-time employment (salary scale 10 under the Collective Labour Agreement for Dutch Universities (CAO NU));
- 8% holiday pay and 8.3% year-end bonus;
- a pension scheme, partially paid parental leave and flexible terms of employment based on the CAO NU.
In addition to the terms of employment laid down in the CAO NU, Utrecht University also offers a range of its own schemes for employees. This includes arrangements for professional development, various types of leave, and options for sports and cultural activities. You can also tailor your employment conditions through our Terms of Employment Options Model. In this way, we encourage you to keep investing in your personal and professional development. For more information, please visit Working at Utrecht University.
Employer
Universiteit Utrecht A better future for everyone. This ambition motivates our scientists in executing their leading research and inspiring teaching. At Utrecht University, the various disciplines collaborate intensively towards major strategic themes. Our focus is on Dynamics of Youth, Institutions for Open Societies, Life Sciences and Pathways to Sustainability. Sharing science, shaping tomorrow.
Working at the Faculty of Science means bringing together inspiring people across disciplines and with a variety of perspectives and backgrounds. The Faculty has six departments: Biology, Pharmaceutical Sciences, Information & Computing Sciences, Physics, Chemistry and Mathematics. Together, we work on excellent research and inspiring education. We do so, driven by curiosity and supported by outstanding infrastructure. Visit us on LinkedIn and discover how you can become part of our community.
You will be part of both the Natural Language Processing group and the National Police Lab AI, both within the Department of Information and Computing Sciences at Utrecht University. The Natural Language Processing group covers both symbolic and statistical approaches to NLP, with particular strengths in explainability, natural language generation, and NLP and society. The National Police Lab AI is a collaboration between the Netherlands Police, Utrecht University and Delft University of Technology. The lab's research focuses on symbolic AI for reasoning, on efficient and explainable machine learning for extracting and structuring information from large datasets, and on combining the two in neuro-symbolic AI.
Additional information
For more information, please contact Albert Gatt (a.gatt@uu.nl) and/or Floris Bex (f.j.bex@uu.nl).
Do you have a question about the application procedure? Please send an email to science.recruitment@uu.nl.
Working at Utrecht University
At Utrecht University, we work together towards a better future for all of us. You are invited to contribute to a better world. Will you join us?
This is a Preview Listing…
You must sign in to see the full job description, and to apply.
Manage / Upgrade this job to a Full Job Listing.
Find Your Best Opportunity
Tell them AcademicJobs.com sent you!
.png){kind=logo}
