Topic: Empowering AI Conversations with Chemical and Biodiversity Knowledge Graphs

Contract limitations
limited contractContact
Your contact for any questions you may have about the job:
Prof. Dr. Jana Schor
Bio-Data Science Group
jana.schor@ufz.de

Your tasks
In this Master's thesis, a Chat Bot Python package will be developed. Large language models (LLMs) will be used and grounded with a knowledge graph of integrated biodiversity and chemical data. Retrieval augmented Generation (RAG) will mitigate knowledge gaps, factuality issues, and hallucinations of (ungrounded) LLMs with external/domain-specific knowledge. The Chat Bot will serve as a user-friendly, human-like interface for non-computer scientists, stakeholders, or the public for the collected data.

The tasks include:

• Craft a knowledge graph from an integrated data collection on biodiversity and chemical monitoring data, and use a graph database to store this data
• Develop a Chat Bot Python package (utilizing an existing in-house prototype) based on large language models
• Develop a retrieval augmented generation solution to ground this LLM with knowledge stored in a Graph Database
• Engineer prompts to allow correct responses to the project-relevant questions
• Provide showcases

We offer

• Excellent supervision that supports your personal and professional development
• Exciting insights into the work of a leading research institute
• The chance to work in interdisciplinary, international teams and benefit from a wide range of perspectives
• The opportunity to contribute and actively shape your own ideas and impulses
  right from the start
• Modern technical equipment and IT service to optimally support your work

Your profile

• Background in Computer Science
• Advanced understanding of large language model (LLMs) APIs
• Solid programming skills in Python
• Experience with software development in an IDE (Jet Brains Py Charm)
• Experience with collaborative software development and agile project management with Git
• Database experience and database querying languages, preferably with graph databases and CYPHER
• Fluent in spoken and written English

Application deadline: 15.11.2024

Diversity and Inclusion
The UFZ has a strong commitment to diversity and actively supports equal opportunities for all employees regardless of their origin, religion, ideology, disability, age or sexual identity.
We look forward to applications from people who are open-minded and enjoy working in diverse teams.

Important
Please submit your application via our online portal with your cover letter, CV (please omit your photo, age, or marital status) and relevant attachments.

Contact
Your contact for any questions you may have about the job:
Prof. Dr. Jana Schor
Bio-Data Science Group
jana.schor@ufz.de