Summary:
This role focuses on applying deep learning to decode the regulatory grammar of plant genomes, translating these predictions into testable biological hypotheses linking genetic variation to ecological roles. You will join the Omics Data Analysis and Integration group at Forschungszentrum Jülich, contributing to the DFG-funded Collaborative Research Centre TRR 341 “Plant Ecological Genetics.”
Postdoctoral Researcher – Machine Learning for Plant Regulatory Genomics, Forschungszentrum Jülich, Germany
Designation: Postdoctoral Researcher
Job Overview Table
| Feature | Details |
| Employer | Forschungszentrum Jülich GmbH |
| Position Type | Fixed-term (3 years) |
| Working Hours | 39 Hours / Week |
| Salary | Pay group 13 TVöD-Bund |
Research Area: Bioinformatics, Computational Biology, Machine Learning, Genomics
Location: Jülich, Germany
Eligibility/Qualification
- Master and/or PhD in Computer Science, Bioinformatics, Computational Biology, Data Science, or a closely related field.
- Strong experience in machine learning and/or deep learning, ideally with sequence models (e.g., CNNs, transformers) applied to genomic data.
- Proficiency in Python and common ML frameworks (e.g., PyTorch, TensorFlow). Experience with HPC clusters is advantageous.
- Familiarity with genomics and regulatory biology (gene expression, transcription-factor binding, variant effects, GWAS/eQTL). A willingness to expand into population and ecological genomics is essential.
- Structured, analytical thinking with a systematic working method.
- Enthusiasm for interdisciplinary collaboration.
- Excellent English skills (written and spoken); working knowledge of German is a plus.
Job Description
As a Postdoctoral Researcher, you will lead the machine-learning core of an interdisciplinary project connecting genomics, deep learning, and plant biology. Key responsibilities include:
- Assembling, harmonizing, and curating large-scale genomic, transcriptomic, and phenotypic datasets into AI-ready resources.
- Developing, re-training, and fine-tuning deep-learning models to predict gene expression and transcription-factor binding from regulatory sequences.
- Applying models to interpret genetic variation and delivering prioritized candidate genes to experimental partners.
- Extending the modeling framework across multiple plant species utilizing transfer learning.
- Presenting results at consortium meetings and international conferences, publishing in peer-reviewed journals, and contributing to open-source tools.
How to Apply
Interested candidates should apply online using the Online application link provided on the job posting page.
Last Date to Apply: August 9, 2026 (09.08.2026)
