Research Associate, Data Scientist, Machine Learning​/ ML Engineer

UE07: £41,064.00 - £48,822.00 Per Annum.

College of Science and Engineering / School of Informatics / Institute for Machine Learning

Full Time - 35 Hours per week.

Fixed Term Contract, if applicable: 01/07/2026 – 31/03/2028 - 21 months.

Together we can do great things. Be part of something bigger.

With roles from hospitality to research,there’sa career for everyone at the University of Edinburgh. We can offer opportunities for you to develop in your career and make a real difference in the communities around us while contributing to the world at large.

The University of Edinburgh is a world‑class organisation. We look for the best in the field across all disciplines and provide a working environment where academics can develop their careers and passion for their chosen subject area. We offer the full range of academic roles and have a genuine focus on our student’s performance and wellbeing.

Improving diagnosis for rare genetic diseases requires innovative, scalable, and explainable machine learning (ML) systems to interpret complex genomic and clinical data. As part of the Welcome Trust funded PARADIGM project, an initiative aiming to transform genomic medicine by identifying new causes of monogenic disease and developing annotated resources for the scientific community. This role will focus on advancing ML pipelines, frameworks, and tools to enhance variant interpretation, gene‑disease models, and clinical decision support.

The successful candidate will collaborate with academics, software engineers, curators, clinical scientists, clinicians, and patient groups to design FAIR (Findable, Accessible, Interoperable, Reusable) and resource‑efficient ML solutions for real‑world deployment. Key responsibilities include developing standards‑compliant, reusable modelling frameworks for rare genetic disease knowledge representation from multi‑modal data, creating scalable and privacy‑preserving computing solutions for genetic and health data, and integrating novel ML technologies into the broader PARADIGM project workflow.

The role also involves proactively disseminating work through national and international collaborations, ensuring explainable AI/ML for clinical use, and supporting students through mentorship and knowledge‑sharing activities.

This position offers the opportunity to contribute to cutting‑edge research, work in the Biomedical Informatics Group, a multidisciplinary team in the School of Informatics, and shape the future of genomic medicine.

• PhD (or near completion) in a relevant field (e.g., Machine Learning, Bioinformatics, Computational Biology, or related disciplines).
• Demonstrated expertise in machine learning, particularly in genomics, rare disease research, or biomedical data analysis.
• Strong ML programming skills in Python and/or other relevant languages, with experience in optimising and deploying distributed compute tasks.
• Experience working with high‑performance computing environments, including containerised systems (e.g., Docker, Kubernetes) for scalable and reproducible computational workflows.
• Ability to work collaboratively within interdisciplinary teams (academics, clinicians, curators, software engineers) and communicate complex technical concepts clearly.
• Experience with scientific writing, including the ability to publish in peer‑reviewed journals and present research findings at conferences.

• Experience with API development and integration, including RESTful APIs or other standards for data exchange and interoperability.
• Familiarity with Model Configuration Protocols (MCP) for defining and deploying machine learning models in reproducible, scalable workflows.
• Experience with database systems (e.g., SQL/No
  
  SQL) and knowledge graph construction (e.g., Neo4j, RDF triples) for organising and querying complex biomedical data.
• Familiarity with tools for data integration, transformation, or workflow orchestration in large‑scale projects.
• Familiarity with ontologies (e.g., HPO, OMIM) and semantic technologies for knowledge graph construction.
• Experience with the use of GNNs in a multi‑modal data integration setting (for example using fusion, hierarchical modelling, contrastive learning).
• Experience with variant‑phenotype mapping, gene‑disease model creation, or computational phenomics.
• Experience with explainable AI/ML and open‑source software development.
• Experience mentoring students (undergraduate, MSc, or PGR) or contributing to educational initiatives.