The German Aerospace Center (DLR) is inviting applications for a Scientist position in the field of GeoAI, specifically focusing on multilingual geo-parsing. This role is based at the Institute of Data Science in Jena and involves working on the DFG-funded project GeoMMCorpus+Eval.
Scholarship Summary
The successful candidate will join the Data Acquisition and Mobilization department (DMO) to develop methods for extracting and processing geographical information from large, heterogeneous text datasets. The project leverages Large Language Models (LLMs) and human-in-the-loop methods to ensure high-quality data annotation and spatial information retrieval.
| Feature | Details |
|---|---|
| Organization | German Aerospace Center (DLR) |
| Designation | Scientist (m/f/d) |
| Location | Jena, Germany |
| Employment Type | Full-time or Part-time |
| Contract Duration | Up to 3 years |
| Remuneration | TVöD-Bund (Public Sector Scale) |
Research Area
The research focuses on GeoAI, Natural Language Processing (NLP), and Multilingual Geo-parsing. Key areas include the creation and annotation of geographical text corpora, LLM-supported quality assurance, and the development of workflows for processing unstructured data from websites, social media, and academic publications.
Eligibility/Qualification
Applicants must meet the following criteria:
- A completed academic degree (Master’s or University Diploma) in Computer Science, Data Science, Geoinformatics, Computational Linguistics, or a related field.
- In-depth knowledge and practical experience in natural language processing (NLP), information extraction, and machine learning.
- Practical experience with Large Language Models (LLMs), including prompting and fine-tuning.
- Proficiency in Python programming and version control tools like Git.
- Ability to work independently on scientific research questions and plan experiments.
- Excellent written and spoken English skills.
- Advantageous: Knowledge of geoinformation processing or GeoAI.
Scholarship Description
As a Scientist at DLR, your primary responsibilities will include:
- Contributing to the DFG project GeoMMCorpus+Eval.
- Designing scientific methods for the extraction and selection of multilingual text datasets.
- Developing data science workflows for cleaning and filtering large corpora from diverse genres.
- Planning experimental studies on LLM-assisted annotation and iterative quality assurance.
- Designing quality metrics to evaluate research results.
- Collaborating within the Multimodal and Spatial Information Retrieval (DMO-MIR) group to make unstructured data machine-readable for decision support.
How to Apply
Interested candidates should apply through the DLR careers portal using the Vacancy-ID 6423. For specific questions regarding the position, you may contact:
Dr. Friederike Klan
Telephone: +49 3641 30960 555
Last Date for Apply
The starting date is as soon as possible. Applications will be reviewed on a rolling basis until the position is filled.
