Research Scientist in LLMs for Scientific Data Exploration
SIB - Swiss Institute of Bioinformatics
Zurich, Switzerland
Job description
Reporting to a Team Lead at the Knowledge Representation Unit, the successful candidate will play an important role in shaping key scientific projects within this Unit, as part of a team of researchers and software engineers. Additionally, the applicant will contribute to publications in top-tier journals and conferences in the field, as well as defining research directions for the future of the Unit.
The main activities will be:
- To build upon state-of-the-art Large Language Models for developing innovative question answering systems over scientific data sources available as Knowledge Graphs;
- To leverage LLMs for Knowledge Graph construction (e.g., triple extraction from unstructured data);
- To contribute to the implementation of a system for generating SPARQL queries from scientific questions;
- To work on data harmonisation, create data schemas and perform data modelling using Semantic Web Technologies when appropriate;
- To build and maintain knowledge graphs based on the created or adopted data schema;
- To be able to negotiate and coordinate domain experts in life sciences to find an agreement for accurately defining domain-specific semantic models;
- Publish and present the resulting work as peer-reviewed articles at conferences and scientific journals;
- The position is temporary for 3 years, with the possibility of extension.
Profile requirements
- PhD degree in computer science or in a related field with maximum 5 years of relevant experience;
- Hands-on experience using and fine-tuning Large Language Models;
- Experience in Applied Machine Learning and LLMs to generate structured queries (e.g., SPARQL) would be a significant plus;
- Semantic Web Technologies’ expertise (e.g., RDF, RDFS, OWL, SPARQL, SHACL);
- Familiarity with ontology engineering best practices and natural language processing would be a plus;
- Software development (e.g., Python, Rust, Java, version control with Git);
- Experience with life science datasets (including biomedical data) is a plus;
- Proven ability to carry out independent research and software development;
- Excellent oral and written communication skills;
- Track record of publications in top-tier conferences and journals;
- Openness to working in a highly interdisciplinary and dynamic environment;
- Multi-tasking, openness to working on multiple projects with similar responsibilities;
- Proficiency in English is required. Speaking German is a plus but not mandatory.
Apply Now
Don't forget to mention EuroScienceJobs when applying.