Postdoctoral Researcher in Large Language Models and Knowledge Graphs (m/f/d)

HITS is looking for a 
 
Postdoctoral Researcher in Large Language Models and Knowledge Graphs (m/f/d)
 
to join the Machine Learning and Artificial Intelligence (MLI) Group to perform research at the intersection of large language models and knowledge graphs. A known disadvantage of large language models is their lack of factual correctness. Often it is not clear if generated content is factually correct, and even worse, often it is not possible to decide based on the generated output if the answer is correct: The generated content of a large language model sounds confident independently of its correctness.

 The current state-of-the-art approach for making language models more factual is based on so called retrieval augmented generation, where additional input data is appended to a user’s query.
In this project, we want to develop an alternative approach that does not only add additional information to a user’s query, but instead combines inference within a language model with inference on structured data such as knowledge graphs and Bayesian networks, with the goal of making the language model more factual. To this end we develop a joint inference process that combines inference in a transformer model with inference on structured data and derive these inference algorithms in a common theoretical framework.

Your role

• Conduct cutting-edge research in machine learning at the intersection of large language models (LLMs) and structured data such as knowledge graphs
• Publish your research findings at major machine learning conferences such as Neurips, ICML, and ICLR.
• Collaborate with other members of the research group
• Supervision of research interns, bachelor- and master-students.

 
What qualifies you for this job

• PhD in a machine learning related field such as Computer Science, Mathematics, or Physics
• Theoretical knowledge in machine learning
• Publications at conferences such as Neurips, ICML, ICLR, or AISTATS
• Theoretical understanding and practical experience in at least two of the following fields
  • Graph Neural Networks
  • Inference in Knowledge Graphs
  • Inference in Bayesian Networks and Factor Graphs
  • Transformer Models
• Experience in building prototypes in machine learning frameworks such as PyTorch and Tensorflow

 
If you are not familiar with all of the above – this position provides the perfect opportunity to gain experience in the remaining fields.

The environment of this job

• Ideal working environment with our own high-performance computing infrastructure and access to national high-performance computers
• You will work within a highly motivated team of individual researchers in a collaborative working environment
• Our institute provides an interdisciplinary research environment and lots of opportunities for interdisciplinary collaboration
• The MLI research group has connections to world leading industrial (Microsoft Research, Samsung AI, Google Deepmind) as well as academic research labs (Cambridge, Edinburgh, MIT, ETH Zurich).
• This is a temporary position from 1.9.2024 – 31.8.2025.

 
HITS benefits

• Option for location-flexible working
• Extensive social benefits, such as: 
  • Subsidized cafeteria meals 
  • Job ticket
  • Allowance for further training and career development 
  • Company pension plan and additional health care benefits 
  • Many more individually selectable benefits
  • 30 days of paid vacation 
  • Family-friendly working environment 

Learn more about Working at HITS
 
For any additional information regarding the position please contact Jun.-Prof. Dr. Jan Stühmer

• Cover letter, including your motivation
• Curriculum vitae
• Relevant academic certificates
• Summary of research accomplishments 
• Names and contact information for two references. 

HITS gGmbH stands for equal opportunities and we strongly believe that our research benefits from inclusive and diverse teams.