Application Form
Research Fellow (Postdoc) in Data Science

JobRef: 20889
  • Accepted file types: pdf, Max. file size: 12 MB.
  • Accepted file types: pdf, Max. file size: 2 MB.

Research Fellow (Postdoc) in Data Science

Level:Postdoctoral Researcher
POSTED:May 19, 2023
LOCATION:School of Computer Science & Statistics, Trinity College Dublin
Duration:24 months
Reports to:Dr David Selby, Professor Mark Little & Professor Lucy Hederman
Salary:€42,032 - €48,427 (according to SFI Level 2 Research Fellow salary scale, on point commensurate with experience), plus funding for additional training and conference travel
Closing Date:July 3, 2023

Please note the strict deadline for application is 3rd July 2023. Applications received after this deadline will not be considered.

Please download the full job spec by clicking the button above for further details.

Post summary

Applications are invited for a talented and motivated data science engineer to join a collaborative project between the Trinity Kidney Centre, the School of Computer Science and Statistics, the ADAPT Research Centre and the German Research Centre for Artificial Intelligence, DFKI, helping to bridge the gap between artificial intelligence and cutting-edge medical research. You will be responsible for developing and maintaining data science pipelines that enable reproducible and effective statistical modelling of rare diseases from sensitive electronic health record data, and in writing and extending statistical software to implement modern machine learning methods. The work will focus on modelling and maximising data quality and alignment with relevant data standards. The successful candidate will work at Trinity College while being jointly supervised by researchers from DFKI.


Background to the Post

The successful candidate will work with Professors Mark Little (, Lucy Hederman ( and David Selby (;  The project is linked to an ERA PerMed-funded consortium called PARADISE (Personalisation of relapse risk in autoimmune disease), which seeks to generate predictive algorithms for relapse in the rare autoimmune disease ANCA vasculitis. The proposed project leverages an extensive rare disease registry and biobank to generate a longitudinal granular phenotype which we aim to link to biomarker, environmental and wearable device data streams. The post will be primarily physically based in Dublin focusing on development of methods for the analysis of rare autoimmune disease data, supported by an interdisciplinary team including statisticians, clinicians, data scientists and patient partners to extract insights from a longitudinal patient dataset. The work will be remotely supervised by the Data Science and its Applications research department of the DFKI, based in Kaiserslautern, Germany. Part of the data science engineer’s time will also be spent on development of statistical software for the extension of modern machine learning models to complex time-to-event or high-dimensional medical data, with the opportunity for secondments in Kaiserslautern.


Standard Duties and responsibilities of the Post

  • The post holder will be a data scientist required to undertake research on projects developing algorithms linking multi-modal assessments of immune system activation and clinical status.
  • Implement machine learning algorithms and data processing pipelines as reusable, modular software packages following best programming practices.
  • Disseminate research findings with the preparation and publication of results in leading international journals.
  • Attend and present research internally and at national and international conferences.
  • Participate and assist/train colleagues in related research projects
  • Prepare reports and professionally engage with academic and industrial partners.
  • Leadership within the PARADISE consortium and DFKI, including helping to run symposia, group meetings and guidance of junior team members.


Person Specification


PhD in data science, computer science, biostatistics, computational biology, machine learning or a similar field.

Knowledge & Experience

  • Appreciation for challenges of longitudinal analysis of sparse, real-world patient data
  • A solid understanding of data science pipelines, version control, software and data testing and best practices
  • An interest in reproducibility, transparency, data ethics, algorithmic fairness and other aspects of responsible data science
  • Awareness of concepts such as personalized medicine, hybrid machine learning or data augmentation
  • Ability to balance technical requirements with making complex concepts understandable to stakeholders and collaborators
  • The ability to work independently on a project, as well as co-operatively within a team, is essential.

Skills & Competencies

  • Proficient in R (essential) and at least one of the Python or Julia programming languages (desirable), with experience in package development
  • Must be a well-organized data scientist with:
    • excellent writing, communication and interpersonal skills
    • Non-native English speakers require at least IELTS 6.5 (with at least 6 in all components) or equivalent.


Application Process

To apply, please submit a brief cover letter describing relevant experience and a PDF copy of your CV along with names and contact information for 2 referees via the following link:

The above can also be e-mailed directly to ADAPT Office Manager Robin O’Driscoll:

Informal enquiries can be sent to Professor Mark Little:


Further Information for Candidates

URL Link to School:

URL Link to Research Group:

URL Link to Human Resources:


Background​ ​to​ ​the​ ​ADAPT centre

We live in a world of global digital connectivity where individuals, communities and businesses are communicating globally at incredible speed, in enormous volumes, across the world’s languages and over an ever-increasing range of devices. ADAPT’s vision is to leverage this torrent of digital content to enable unprecedented levels of global engagement among people, companies and communities. This is achieved through a unique collaboration between world-class research groups in multilingual natural language processing (NLP), multimedia content analysis and transformation, personalisation and multimodal interaction. Within ADAPT and its affiliated group of international and commercialisation projects, these posts will deliver the advances in linked data and semantic technologies that are key to efficiently manage the content, language and knowledge assets that underpin intelligent global customer engagement.


Background​ ​to​ ​DFKI

The German Research Centre for Artificial Intelligence GmbH (DFKI) was founded in 1988 as a non-profit public-private partnership (PPP). The DFKI combines top scientific performance and business-related value creation with social appreciation. The DFKI has been researching AI for humans for over 30 years and is oriented towards social relevance and scientific excellence in the decisive future-oriented research and application areas of artificial intelligence. In the international scientific world, the DFKI is one of the most important “Centres of Excellence”.

Within the DFKI, the Data Science and its Applications research group is a constellation of researchers who—while geographically and institutionally spread—are united under the supervision of Professor Sebastian Vollmer, with a shared goal of advancing data science methods and tools, and using them across industrial and socially-important applications.

Apply Now

Other Positions