Research Engineer (RE123)

Institution/Company:
Barcelona Supercomputing Center - Centro Nacional de Supercomputación
Location:
Barcelona, Catalonia, Spain
Job Type:
  • Programmer/Developer
Degree Level Required:
Bachelor's, Masters
Apply Now

Research Engineer (RE123)

Professor Nataša Pržulj is looking for a Research Support Engineer to work in her Integrative Computational Network Biology (ICONBI) group (overview of the group is at https://www.bsc.es/discover-bsc/organisation/scientific-structure/integrative-computational-network-biology-iconbi).The post-holder will participate in the process of finding, designing and implementing new algorithms, Data Science and AI solutions to challenges related to the research projects the group is working on.

The ICONBI research group performs research in the design of novel network science and machine learning algorithms carefully tuned to extract new biomedical information from systems-level omics data to aid Personalized Medicine. The group actively collaborates with researchers from other fields, with the goal of applying machine learning to challenging problems in systems biology and precision medicine. The group is involved in multiple research projects, including the prestigious ERC Consolidator grant of Prof. Pržulj. Although ICONBI is open to all aspects of algorithmic development and AI, currently the main lines of research are omics data fusion by non-negative matrix tri-factorization (NMTF) and graph (or network science) algorithms.

The Researcher will work in a highly sophisticated HPC environment, will have access to state-of-the-art systems and computational infrastructures, and will establish collaborations with experts in different areas both at the local and international levels.

Responsibilities:

Education

  • BSc in Computer Science, Applied Mathematics, or a related discipline
  • MSc in Bioinformatics, Computer Science, Artificial Intelligence, Machine Learning, or a related discipline

Essential Knowledge and Professional Experience

  • Good knowledge of C/C++ and Python
  • Knowledge of Test-Driven Design and/or Development
  • Knowledge of Continuous Integration/Delivery/Deployment, including tools such as (or similar to) Terraform, GitLab CI, Docker and/or Ansible
  • Knowledge of mathematics, optimization and statistics applied to Machine Learning
  • Knowledge of molecular data and bioinformatics tools and algorithms

Additional Knowledge and Professional Experience

  • Knowledge of: Javascript/node.js, C#, Matlab and/or Java
  • Experience in machine learning and data mining, including knowledge of Keras, PyTorch, Tensorflow, Pandas, Scikit-learn and/or Numpy.
  • Knowledge of agile methodologies for project management, eg. Kanban
  • Experience in optimisation and parallelisation, ideally in HPC clusters
  • Theoretical broad knowledge of AI techniques, such as Deep Neural Networks, Natural Language Processing (NTLK), Reinforcement Learning
  • Experience in configuring and querying Database Systems, such as SQL (e.g. MySQL) and NoSQL (e.g. MongoDB, Elasticsearch), and in Unix
  • Experience in working with source code repositories (e.g. Github, BitBucket, etc.)
  • Experience in -omics bioinformatics techniques, including NGS data processing pipelines (mapping, variant calling, filtering, etc), integration of clinical and experimental data from different sources, reproducibility and portability of analysis workflows
  • Experience using public databases (Reactome, OMIM, GO, PharmGKB, PDB, TCGA, ClinVar, dbSNP etc)
  • Experience in research and in dissemination activities, including paper writing

Competences

  • Fluency in spoken and written English
  • Capacity to explore new research lines
  • Good communication and presentation skills
  • Ability to work within a team and within a pair (pair programming)

Qualifications:

  • Work, in collaboration with the members of the group, on the design and implementation of new Machine Learning and other algorithms and solutions needed to achieve the goals of the group’s research projects
  • Interact with relevant stakeholders of the group’s research projects to understand their problems and the available data in order to formulate useful algorithmic solutions
  • Provide processing, quality and annotation of NGS and other omics data sets, as needed
  • Implement and maintain the source code, the software platform and any required databases for storing and manipulating the omics data with the group’s new methods
  • Data visualization and report generation
  • Develop web interfaces for the computational solutions of the group, that provide data analytics, interpretation and dissemination
  • Contribute to the design and development of HPC and cloud-based workflows and software solutions required by the group
  • Maintain the group’s web pages and provide online dissemination of the group’s results
  • Provide support in the design and preparation of new projects
  • Follow software development best practices
  • Maintain a current knowledge of related technologies
  • Collaborate with the members of the group in the project management activities