Company
Barcelona Supercomputing Center - Centro Nacional de Supercomputación
Company Website
Where
Info
Full Time
Closes: 31 July 2024
Applications have closed
  • July 31, 2024
  • Data Scientist for Big-Data Analytics Platforms, Genomics and Healthcare (RE2-R2)

    Context And Mission

    The Data-Centric Computing group from the Computer Science department at the Barcelona Supercomputing Center is searching for Data Scientist to work on High-Performance Data Analytic (HPDA) platforms and Medical Synthetic Data Generation. Mainly, time series analytics and generative models.

    The main objective is to participate in two European research projects. The first is focused on developing methods to predict and estimate the resources requires by HPDA applications to better understand their behaviour and provide information to an orchestrator to manage them. The applications are ran in Big Data and Serverless frameworks such as Apache Spark or Lithops. The methods should use time series information to create an estimation of the resources and also a prediction of them over time. This work is performed in collaboration with Genomic researchers as the applications are focused on genomics analytics. The second is focused on developing models to generate Medical Synthetic Data (Generative AI), data that resembles to the original data provided but it cannot be traced back to the original data. In particular we focus on the development of models to generate synthetic images, but the position might not be limited to that. This work is performed in collaboration of hospitals from the European Union.

    Both projects involve collaborating with researchers both from BSC and external and actual use cases. This includes communicating research results in project meetings with the rest of the partners online and presential (might require to travel outside of Spain twice a year).

    Key Duties

    Development of methods to estimate and predict application resource usage
    Development and integration of Synthetic Data Generation models for healthcare
    data
    Usage and metric extraction of Cloud/Serverles HPDA/ML platforms and
    applications (e.g., Apache Spark, Kubernetes,…)
    Contribution to the development of predictive models for HPDA/ML platforms
    for orchestration of applications
    Participation in internal and external meetings
    Give mutual support to other workers in the projects

    Requirements

    EducationMaster in Computer Science, Data Science, Artificial Intelligence or similar
    Essential Knowledge and Professional ExperienceA PhD in these fields is valued
    Skills on Software Engineering
    Skills on Software Engineering
    Basic knowledge on infrastructure (cloud/edge computing, serverless computing)
    Knowledge of Python
    Skills in Deep Learning frameworks such as PyTorch
    Additional Knowledge and Professional ExperienceKnowledge in time series modeling
    Knowledge in Generative AI, specially image generation
    CompetencesBasic skills on system administration
    Basic skills in using distributed environments and databases

    Conditions

    The position will be located at BSC within the Computer Sciences Department
    We offer a full-time contract (37.5h/week), a good working environment, a highly stimulating environment with state-of-the-art infrastructure, flexible working hours, extensive training plan, restaurant tickets, private health insurance, support to the relocation procedures
    Duration: Open-ended contract due to technical and scientific activities linked to the project and budget duration
    Holidays: 23 paid vacation days plus 24th and 31st of December per our collective agreement
    Salary: we offer a competitive salary commensurate with the qualifications and experience of the candidate and according to the cost of living in Barcelona
    Starting date: 01/09/2024