Data Scientist in AI - Department of Cancer Research

The Luxembourg Institute of Health (LIH) is seeking a highly motivated Data Scientist in AI with strong expertise in one or several of the following data types: multi-omics (e.g., DNA-seq, RNA-seq, proteomics), single-cell technologies, and foundation models in biomedicine.
The successful candidate will support the expanding research activities at theDepartment of Cancer Research (DoCR) and the Department of Medical Informatics (DMI) with a particular emphasis on high-throughput, reproducible, service-oriented bioinformatics for cancer research programs, with a strong focus on sequences, multi-omics data, and single-cell datasets. In collaboration with DoCR researchers, she/he will engage in cutting-edge research and applied projects using machine learning, deep learning, and omics data analysis

Key Accountabilities

• Support research groups in the planning and implementation of AI-driven analyses of molecular data, focusing on single-cell and bulk multi-omics and long-read sequencing.
• Develop, train, and validate machine learning and deep learning models for multi-omics integration to learn the shared and modality-specific representations across multiple data types.
• Use pre-trained foundation models developed for biological sequences or single-cell and bulk omics. Fine-tune large models for specific tasks, e.g., variant effect prediction, cell state representation, annotation, perturbation prediction, and classification.  
• Generative AI for omics: develop and apply probabilistic generative models (e.g., VAEs and related approaches) for modeling omics data.
• Implement and maintain scalable pipelines for protein structure prediction, including state-of-the-art tools such as AlphaFold. Perform digital drug screening with the existing tools.
• Work closely with biologists, clinicians, biostatisticians, and computer scientists, support their AI/ML needs, and translate research into real-world applications.
• Contribute to the training of LIH staff members and PhD students.

Key Skills, Experience and Qualifications

• MSc/PhD degree in computer science, biomedical engineering, data science or related.
• At least 2 years of experience in a similar position.
• Expertise in AI/ML and deep learning methods, with a rigorous approach to model evaluation and validation. Experience in handling and understanding omics data.
• Strong programming skills in Python. Knowledge of R is considered an asset.
• Proficiency with modern deep learning frameworks, such as PyTorch and TensorFlow.
• Experience working in high-performance computing (HPC) environments: use of cluster computing, job schedulers, and containerization.
• Excellent problem-solving, organizational, and time-management skills.
• Strong communication skills and ability to work effectively in a team and in close collaboration with biologists and clinicians.
• Self-motivated, team spirit, and service-oriented mindset.
• Language skills: fluent command of English. Knowledge of French and/or German is considered an advantage.

Kindly note that this role is subject to a 12-month probationary period.