PostDoc (m/f/d) - Large Language Models for Metadata Extraction and Scientific Data Infrastructures

PostDoc (m/f/d) - Large Language Models for Metadata Extraction and Scientific Data Infrastructures, 1. imagePostDoc (m/f/d) - Large Language Models for Metadata Extraction and Scientific Data Infrastructures, 2. image

Technical University Munich (TUM) operates the high flux Neutron Source Heinz Maier-Leibnitz (FRM II) located at the scientific campus in Garching, Germany. The neutron source itself, its research instruments as well as the irradiation facilities provide unique possibilities for the scientific and industrial use of neutron beams.
In the field of research data management, we invite applications for a full time (40h / week) position as PostDoc (m/f/d) - Large Language Models for Metadata Extraction and Scientific Data Infrastructures.

Tasks and Responsibilities

As part of a national collaborative project aimed at advancing research data management (RDM) in the photon and neutron sciences (PaN), TUM is working together with partners on innovative methods for the automated extraction and utilization of metadata based on modern AI technologies. The goal is to make complex experimental data more accessible and usable through semantic enrichment, standardization, and intelligent query methods.

The TUM contribution focuses in particular on the implementation and integration of the developed models into the software infrastructure of the Heinz Maier-Leibnitz Zentrum (MLZ), as well as on the development of methods for automated code generation for neutron data analysis.

In an interdisciplinary team across institutes, you will contribute to:

  • Implementation and integration of LLM-based methods for automated metadata extraction and ingestion into the data infrastructure of FRM II / MLZ
  • Development of robust pipelines for the extraction, harmonization, and standardization of metadata from heterogeneous sources (e.g., publications, HDF files)
  • Adaptation and optimization of large language models for scientific applications in neutron research
  • Contribution to the development and implementation of ontologies and knowledge graphs for the semantic linking of experimental data
  • Development of systems for translating natural language into structured data queries (e.g., SPARQL)
  • Contribution to the development of an LLM-based assistant system to support experiment planning and metadata capture
  • Participation in the automated code generation for neutron data analysis
  • Close collaboration with project partners (including Forschungszentrum Jülich, KIT, Hereon) as well as initiatives such as DAPHNE4NFDI
  • Evaluation and validation of the developed methods using real user data and diverse user groups

Qualification and Experience

  • Completed PhD in physics, computer science, data science, or a related field
  • Strong expertise in machine learning / natural language processing, ideally with a focus on large language models
  • Experience with Python and modern ML frameworks (e.g., PyTorch, TensorFlow, Hugging Face)
  • Knowledge of data formats and standards (e.g., HDF5, NeXus) is an advantage
  • Experience with semantic technologies (ontologies, RDF, SPARQL, knowledge graphs) is desirable
  • Interest in large-scale scientific facilities and experimental research (in particular neutron or synchrotron radiation)
  • Ability to work in interdisciplinary teams and communicate with scientific user communities
  • Excellent command of written and spoken English


For further information please contact Mr. Michael Schulz, phone +49 89 289 14718, E-Mail: Michael.Schulz@frm2.tum.de

The high safety standard of our facility requires the reliability of the employees according to German nuclear law. Appropriate reliability checks have to be performed for all employees.
https://www.gesetze-im-internet.de/atz_v

 

Perks

The appointment is initially limited to 3 years. Salary payment is based on the German pay scale TV-L. 


Technical University Munich is an equal opportunity employer. Therefore, women are especially encouraged to apply. The position is suitable for severely disabled persons. Severely disabled applicants will be given preference in the event of otherwise essentially equal suitability, ability and professional performance.

TUM benefits include

  • TUM sports and health programs
  • TUM-internal training courses (e.g. language courses and lifelong learning)
  • TUM childcare
  • good connection to public transportation

 

Contact

We are looking forward to your application

until August 13, 2026.

Here you may also find other job vacancies at FRM II:
https://karriere.frm2.tum.de


Technical University Munich
Research Neutron-Source
Heinz Maier-Leibnitz (FRM II)
Personnel Office
Lichtenbergstraße 1
D-85748 Garching
Tel: +49 89 289 13815 or 12305 or 14910

www.mlz-garching.de
www.frm2.tum.de

As part of your application, you provide personal data to the Technical University of Munich (TUM). Please view our privacy policy on collecting and processing personal data in the course of the application process pursuant to Art. 13 of the General Data Protection Regulation of the European Union (GDPR) at https://portal.my-tum.de/kompass/datenschutz/Bewerbung/ By submitting your application, you confirm to have read and under-stood the data protection information (https://www.tum.de/spezialseiten/datenschutz/) provided by TUM.