Postdoctoral Researcher in Artificial Intelligence (AI) and Data Science

The project addresses critical challenges in personalized medicine, disease stratification, and multi-modal data fusion, enabling next-generation solutions in precision health and biomedical research.

Scientific Challenges Addressed in the Position

• Heterogeneity and high dimensionality of multi-omics data requiring advanced AI/ML methods for robust analysis and integration.
• Data sparsity, batch effects, and missing values across different omics layers and platforms.
• Cross-omics data fusion and representation learning for comprehensive systems biology modeling.
• Identification of causal relationships and biomarker discovery through integrative approaches.
• Time-series and longitudinal multi-omics data analysis for disease progression modeling.
• Explainability and interpretability of AI models to support clinical decision-making and regulatory compliance in healthcare settings.
• Scalability and computational efficiency in processing and integrating massive multi-omics datasets from clinical cohorts.

Key Responsibilities

• Design and implement AI/ML pipelines for multi-omics data integration, including supervised and unsupervised learning methods.
• Develop deep learning architectures (e.g., variational autoencoders, graph neural networks, transformers) for cross-omics data representation and feature extraction.
• Apply multi-view learning, transfer learning, and data fusion techniques to integrate heterogeneous omics datasets and clinical metadata.
• Conduct network-based analysis (gene regulatory networks, protein-protein interaction networks, metabolic networks) to identify key disease drivers and biomarkers.
• Build predictive models for disease classification, patient stratification, and treatment response prediction.
• Collaborate with biologists, clinicians, and bioinformaticians for data interpretation and validation of computational findings in clinical or experimental settings.
• Disseminate research outcomes through publications in high-impact journals, conference presentations, and workshops.
• Mentor and support the training of graduate students and early-career researchers in AI and multi-omics integration.

Required Qualifications

• Ph.D. in Bioinformatics, Computational Biology, Data Science, Artificial Intelligence, or a related field.
• Proven experience in multi-omics data integration, omics data analysis (genomics, transcriptomics, proteomics, metabolomics, microbiome).
• Strong expertise in machine learning, deep learning, and advanced AI frameworks (TensorFlow, PyTorch, Scikit-learn). Experience with bioinformatics tools and databases (e.g., Bioconductor, Galaxy, KEGG, Reactome, STRING).
• Proficiency in Python, R, and Unix/Linux-based environments for high-performance data analysis. Knowledge of biological network inference, causal modeling, and graph-based AI approaches.
• Experience in multi-modal data fusion, representation learning, and heterogeneous data integration.
• Strong publication record in relevant peer-reviewed journals.
• Excellent communication skills and ability to work in a multidisciplinary environment.
• Familiarity with cloud-based computing platforms (AWS, Azure, Google Cloud) and high-performance computing (HPC) environments.
• Understanding of data privacy, security, and ethical considerations in handling clinical data.

Application Process

Interested candidates should submit the following documents in a single PDF:

1. A cover letter outlining their research interests, motivation, and relevant experience.
2. A detailed Curriculum Vitae (CV) with a list of publications.
3. Contact details of two academic referees.