Context And Mission

The Machine Learning for Biomedical Research unit at the BSC, led by Dr. Davide Cirillo, is currently offering a postdoctoral researcher position. This role focuses on employing Artificial Intelligence (AI) techniques to synthesize various types of biomedical data, including images, genomic sequences, time series, and texts. Synthetic data generation in biomedicine involves creating artificial datasets that mimic real biological data, which is crucial for enhancing privacy protection, increasing data availability, reducing biases, ensuring regulatory compliance, and facilitating more robust and cost-efficient research and development. This initiative is part of a collaborative project supported by an EU public-private partnership, aimed at advancing the frontiers of synthetic data generation in biomedical research.
The Life Sciences Department at the BSC is renowned for its pioneering independent research led by senior scientists. The department's expertise spans the application of computer science to life sciences, encompassing healthcare applications of machine learning and AI, as well as leveraging High-Performance Computing (HPC) for biomedical research pursuits. The Machine Learning for Biomedical Research unit is an integral component of this department, engaged in several projects that range from computational systems biology and network science to digital medicine. More about the unit can be found here:
https://www.bsc.es/discover-bsc/organisation/research-departments/machine-learning-biomedical-research
The selected candidate will collaborate extensively with senior researchers within the Life Sciences Department and other research groups at the BSC. The research will align with the unit's focus on AI applications in Personalized Medicine, which includes synthetic data generation, complex systems modeling, and agent-based simulations.
The researcher will operate within a sophisticated HPC environment, with access to cutting-edge systems and computational infrastructures. The role involves extensive collaboration with both international and local experts across public and private sectors. The researcher will develop and implement systems for creating synthetic datasets, which will be pivotal for training and evaluation processes.
Applicants should possess a robust understanding of a broad spectrum of biomedical data and be proficient in deep learning techniques. Familiarity with privacy-preserving AI and explainable AI (XAI) is preferred, enabling the development of innovative and ethically sound AI solutions.
This position offers an exceptional opportunity to contribute to significant advancements in AI-driven biomedical research, working in a dynamic and collaborative international research environment.

Key Duties


- Develop computational solutions, with special emphasis on AI methods, for the generation of synthetic instances of biomedical data of different types and modalities.
- Implement robust and reliable state-of-the-art generative models, such as Transformers, Diffusion models, Variational Autoencoders (VAE), Generative Adversarial Networks (GAN).
- Interact efficiently with the HPC environment of the Barcelona Supercomputing Center.
- Explore the application of explainability to the required tasks.
- Demonstrate skills in scientific communication.
- Establish and maintain collaborations with national and international researchers in both the public and private sector in the area of healthcare and biomedical research.


Requirements


Education
- PhD in computer science or bioinformatics with a very strong AI component.
- Alternatively, an MSc on AI or Bioinformatics, with a strong computer science background, or background on applied mathematics/physics with demonstrated experience in AI methods.
Essential Knowledge and Professional Experience
- Experience in AI methodologies, specifically biomedical data analysis.
- Deep learning frameworks (PyTorch, TensorFlow)
- Interest in the life sciences area
Additional Knowledge and Professional Experience
- Experience in synthetic data generation
- Knowledge and experience in life sciences research
- Knowledge and experience in machine learning and data science:
▪ Data pre/post-processing (feature selection, feature reduction, plotting and visualization)
▪ Supervised and unsupervised learning (classification, regression, clustering)
▪ Model deployment and scaling strategies (Docker, Kubernetes)
- Programming: Python (scikit-learn, numpy, matplotlib), R, Java, C, C++, Git.
- Fluency in spoken and written English
Competences
- Capacity to explore new research lines
- Good communication and presentation skills
- Ability to work both independently and within a team