Software Engineer EPI-FLARE

ISGlobal is seeking a Software Engineer to implement and maintain a platform for episignatures (EPIFLARE - Diagnosis of rare neurodevelopmental disorders using integrated epigenomics within a secure federated learning framework). We aim to consolidate, optimize and clinically validate a privacy-preserving platform that improves the diagnosis of neurodevelopmental and rare disorders.

The candidate will join the Bioinformatics Research Group in Epidemiology (BRGE), led by Dr Juan Ramón Gonzalez, within the Environment and Health over the Lifecourse research programme. The group develops reproducible, secure methods for analysing sensitive clinical and omics data in multidisciplinary settings.

EPI-FLARE enables federated access to clinical and epigenomic data held at participating hospitals. Its architecture combines Opal and DataSHIELD with the dsHPC infrastructure, a request-handling API, Slurm-based execution in R and Python environments, result caching, audit trails, secure R Shiny visualization and a web-based administration panel. Only non-disclosive outputs leave each institution.

The Software Engineer will optimize analytical pipelines for epimutations, episignatures, copy-number variants (CNVs) and developmental epigenetic age; adapt and secure the platform for hospital deployment; and support clinical validation and usability testing. The role is central to the platform's reliability, scalability, GDPR compliance and long-term sustainability.

• Implement and maintain the EPI-FLARE platform across WPs 1-3 under the supervision of David Sarrat and the Principal Investigator.

• Ensure platform reliability, scalability, reproducibility, interoperability, security, GDPR compliance and long-term sustainability.

• Coordinate software development with bioinformaticians, data scientists, clinicians and hospital IT teams.

• Support hospital deployment, clinical validation, usability testing, documentation and continuous platform improvement.

• Optimize and maintain analytical pipelines for data curation, epimutation and episignature analysis, copy-number variant (CNV) detection, and developmental epigenetic age (WP1, Tasks 1.2-1.4).

• Develop and maintain federated analysis and model-training workflows built on Opal, DataSHIELD and dsHPC, including request APIs, job orchestration, R/Python execution environments, caching and non-disclosive result handling.

• Adapt and secure the platform for deployment in hospital infrastructure, implementing appropriate authentication, access control, encryption, audit-trail logging, monitoring and GDPR-compliant data flows (WP2, Task 2.1).

• Develop and improve secure R Shiny/user interfaces and web-based administration tools for workflow execution, result visualization, system resources, job queues and logs.

  Support automated testing, version control, benchmarking, documentation, deployment and maintenance to ensure reproducible and sustainable releases.

• Support clinical validation and usability testing with partner institutions, resolve technical issues and incorporate feedback from healthcare professionals (WP3, Tasks 3.1-3.3).

• Collaborate with software developers, bioinformaticians, data scientists, clinicians and domain experts to validate the tools and facilitate adoption in real-world clinical settings.

This job description reflects the present requirements of the post but may evolve at any time in the future as duties and responsibilities change and/or develop providing there is appropriate consultation with the post-holder.

This job description is not a definitive or exhaustive list of responsibilities but identifies the key responsibilities and tasks of the post holder. The specific objectives of the post holder will be subject to review as part of the individual professional assessment process.