All new
Data Science
jobs, in one place.

Updated daily to help you be the first to apply ⏱

Diagnostic Data Scientist
  • Python
  • SQL
  • Java
  • Linux
  • Machine Learning
  • Data Analysis
  • Excel
  • Database
  • Scala
  • NoSQL
  • Unix
131 days ago

In AstraZeneca we are on a journey to become a data-led enterprise with a solid and ambitious investment in R&D. We’re capitalising like never before in our people, in growth, in pursuing excellent science and adopting new technologies. The Diagnostic Science group within Precision Medicine in AstraZeneca transforms data and innovative technologies into future diagnostic options to match patients’ needs. We are a cross-functional group deeply focused in enabling digital, data-driven diagnostics that match AstraZeneca’s business needs of today and of the future.

The Diagnostic Science team is building a visionary Deep Medicine Data Platform that interacts with state-of-the-art scientific data platforms. The platform will integrate multi-modality scientific data, and facilitate analysis of large-scale genomics, imaging and other emerging modalities applying cloud, AI and machine learning technologies. This role will also include optimising existing capabilities and identifying opportunities, both internally and through an extensive network of partners, vendors and open source tools to build and maintain efficient, robust and scalable solutions supporting diagnostic models’ development.

As a member of the Diagnostic Science group, you will contribute to the vision, design, implementation and deployment of Precision Medicine diagnostics & scientific software solutions , bioinformatic pipelines and workflows to support all aspects of innovative diagnostics products development.

You'll support the management, exchange, processing, analysis, curation, annotation and sharing of scientific and clinical data with colleagues within Precision Medicine & Biosamples team and throughout AstraZeneca, and in international collaborations.

You will be part of the multidisciplinary diagnostic science team comprising of computational biologists, machine learning experts, software engineers, postdoctoral researchers, disease area specialists and clinician experts contributing novel ideas and developing prototypes of algorithms and analytical approaches impacting current and future patient journeys.

Typical Accountabilities, what you will be doing:

  • Manage Platform data exchange with collaborators, ingestion, annotation and making the data analysis ready.
  • Development, deployment and support of Precision Medicine data analysis software and bioinformatic workflows and pipelines.
  • Integrating 3rd party software (commercial and open-source) with bespoke components to build end-to-end diagnostics data analytic and informatic software solutions.
  • Integrating with internal federated data systems components to build end-to-end diagnostics data analytic and informatic software solutions.
  • Automating processes to improve efficiency of the platform interaction with diagnostic data and with downstream analysis platforms.
  • Developing methods of visualising, exploring and mining multi-modality diagnostic data.
  • Ensuring the high quality of the code and adherence to industry standards and best practices for all stages of software lifecycle.
  • Ensuring own work, and work of team, is compliant with Good Laboratory Practice, Safety, Health and Environment standards and all other internal AstraZeneca standards and external regulations as they apply.

Education, Qualifications, Skills and Experience:


  • Master’s degree (or equivalent experience) in a computational field of research, including but not limited to: computer science, bioinformatics, information systems, computational genomics/imaging or other computationally intensive scientific field.
  • Manage existing and newly created scientific pipelines.
  • Significant Java/Scala or Python programming experience.
  • Significant database implementation experience (relational and/or NoSQL).
  • Experience with modern JS framework applied to building interactive scientific visualisations, ability to create UI components and build web user interfaces.
  • Proficiency with UNIX / Linux environment including shell scripting.
  • Knowledge of genomics/digital imaging community algorithms and solutions. Interest in the potential of genomics and/or imaging to impact novel diagnostics approaches or significant relevant experience in scientific computing to support research workflows with automation, model-driven approaches, and dealing with sensitive research data.
  • Ability to prioritize, problem-solve and perform difficult tasks while working to potentially conflicting deadlines.
  • Ability to proficiently communicate with team members and non-experts, both verbally and through documentation.
  • Excellent interpersonal skills and willingness to work within a team in a quickly evolving environment.
  • Detailed knowledge of core computer science concepts (e.g. object-oriented design, memory management, algorithm implementation) and practices (e.g. version control, agile development, Continuous Integration and Continuous Delivery).


  • Java or Python authority.
  • Significant database design experience (relational and/or NoSQL).
  • Experience working in cloud environments, for example with AWS services (S3, Glacier, Batch).
  • Proficiency in collaborative development tools such as Github, Confluence and JIRA.
  • Experience of all phases of software development for large-scale analytical pipelines, including analytical programming, scripting and code review
  • Experience with high performance computing, cloud-based bioinformatics and parallel processing.
  • Experience or good understanding of software containerization technologies
  • Experience in developing or deploying machine learning solutions.
  • Knowledge of project management and software development life cycle.
  • Experience in scouting , evaluation and due diligence of scientific technologies and companies.
  • Experience using and building application programable interfaces such as REST, GraphQL, SPARQL APIs,

Role can be considered at career levels D or E depending on the experience and suitability of the successful candidate.

Location: Cambridge, UK, Gothenburg, Sweden or Gaithersburg or Boston, US

Salary: Competitive + Excellent Benefits

Closing Date: 5th July 2020

Next steps, if you feel you are suitable please apply!


    Related Jobs

  • Data Analyst

    • Database
    171 54 Solna
    7 days ago
  • Data Scientist at Data & Mobility Services– Service Portfolio & Delivery

    • Pandas
    • SQL
    • Hadoop
    4 days ago
  • Data Scientist for service content optimization

    • Machine Learning
    14 days ago
  • Thesis Work - Machine learning for driver behavior classification

    • Big Data
    Volvo Cars
    8 days ago
  • Senior Data Engineer - Analytics and Data Platforms

    • Big Data
    • Power BI
    • Azure
    3 days ago