EMBL knowledge management with LLMs Intern

EMBL is Europe’s life sciences laboratory – an intergovernmental organisation with more than 110 independent research groups and service teams covering the spectrum of molecular biology. It operates across six sites in Heidelberg (headquarters), Barcelona, Cambridge, Grenoble, Hamburg and Rome. Our mission is to perform basic research in molecular biology; train scientists, students and visitors at all levels; offer vital services to scientists in the public and private sectors within the member states; develop new instruments and methods; and engage actively in technology transfer.

The Data Science Centre aims to facilitate research advances in data science, offers internal and external services, tools and resources, develops common representations (data, conventions, workflows) and contributes to training and career development. The Data Science Centre collaborates with all EMBL sites to progress internal and external training, integrated data management, scientific workflow sharing, AI, provision of public data services, and technical infrastructure.

As a large organization, EMBL has accumulated internal knowledge on a range of topics, from administrative procedures to scientific and technical matters. However information is scattered across various systems and formats limiting its discovery. We therefore want to develop a more comprehensive knowledge management system leveraging the power of large language models.

With this call, EMBL is seeking an intern at the Data Science Centre. You will be based in Heidelberg, and collaborate with members from EMBL’s Analysis Centres and the Bio-IT support community, as well as the Data Management Coordination.

You’ll be building the basis of an EMBL-wide knowledge management system focusing on a retrieval-augmented generation (RAG) workflow.

• Good programming skills
• Experience with web development
• Good communication and writing skills (e.g. writing documentation)

• Experience with RAG/RAG frameworks
• Knowledge/experience of cloud technologies (e.g. API, Kubernetes …)

We are Europe’s research laboratory for the life sciences – an intergovernmental organisation performing scientific research in disciplines including molecular biology, physics, chemistry and computer science. We are an international, innovative and interdisciplinary laboratory with more than 1900 employees from many nations, operating across six sites, in Heidelberg (HQ), Barcelona, Hinxton near Cambridge, Hamburg, Grenoble and Rome.

Our mission is to offer vital services in training scientists, students and visitors at all levels; to develop new instruments and methods in the life sciences and actively engage in technology transfer activities, and to integrate European life science research. The working language of the institute is English.

Please note that appointments on fixed term contracts can be renewed up to 9 years in total, depending on circumstances at the time of the review.

EMBL is a signatory of DORA. Find out how we implement best practices in research assessment in our recruitment processes here.

Please apply online through: www.embl.org/jobs