Clinical Data and AI Integration Analyst

About us:

CogStack (https://cogstack.org/) is an award winning ecosystem of tools and workflows that facilitate the ingestion, structuring, organising and visualisation of Electronic Health Record (EHR) data built by a multidisciplinary team of software developers, machine learning engineers, clinical researchers and health informaticians. The CogStack team is at the forefront of building impactful solutions and partnering with NHS Trusts and healthcare providers, tackling real world clinical problems supporting use cases from state-of-the-art clinical research through to translational research delivering innovative solutions for direct patient care (How Elastic improves patient outcomes with valuable healthcare data; https://doi.org/10.1101/123299).

About the role:

The Clinical Data Linkage Service (CDLS), hosted by the NIHR Maudsley Biomedical Research Centre (BRC), provides secure and ethical linkage between datasets from King’s College Hospital (KCH), Guy’s and St Thomas’ NHS Foundation Trust (GSTT), and the Clinical Record Interactive Search (CRIS) platform at South London and Maudsley NHS Foundation Trust (SLaM).

The postholder will support and maintain the use of CogStack to extract and process clinical data at KCH and GSTT for linkage to CRIS via the CDLS. This includes working closely with CogStack colleagues, data controllers, research teams and operational stakeholders across Trusts to ensure high-quality, auditable and timely data processing pipelines.

The post holder will be expected to be able to contribute to the following areas:

• Operational support for running and maintaining CogStack pipelines at KCH and GSTT, with a focus on secure, high-quality, and auditable EHR data extraction for the CDLS.
• Implementation and documentation of ETL workflows to map data to CDLS and CRIS data structures.
• Contribution to the technical specification and troubleshooting of issues arising in clinical data provisioning, NLP processing, or linkage preparation.
• Extension of CogStack-NiFi or other internal modules for custom data routing, transformation or enrichment tasks (e.g. MedCAT NER+L).
• Data quality assessment and contribution to the development of automated or manual quality control tools for clinical datasets.
• Communication of requirements and constraints to clinical and non-technical audiences, especially in relation to information governance and linkage protocols.
• Collaboration with the broader CogStack team to ensure architectural alignment, reusable components, and long-term platform sustainability.

This is a full time post (35 hours per week), and you will be offered a fixed term contract until 30/11/2027.

About you:

Essential criteria

• MSc or equivalent experience in a relevant area such as computer science, health informatics, software engineering, or data science
• Experience with Python and/or Java for data engineering or EHR processing tasks
• Experience with ETL workflows, database systems (e.g. PostgreSQL, SQL Server), and API-based data integration
• Knowledge of data security, audit logging and information governance in healthcare settings
• Experience working with version control (e.g. Git), DevOps practices and container technologies such as Docker
• Strong communication skills and ability to work across multi-disciplinary and cross-organisational teams

Desirable criteria

• Experience working in or with NHS Trusts or other health data environments
• Experience with MedCAT, CogStack-NiFi or similar clinical NLP tools
• Understanding of CRIS or similar de-identified research platforms
• Experience managing complex or high-volume data pipelines in production environments
• Knowledge of FHIR, SNOMED CT or other healthcare interoperability and ontology standards

Advert information