Senior Data Scientist - Biomedical Knowledge Graphs

‎

About the opportunity

Join QIAGEN Digital Insights in Cluj-Napoca and help transform complex biomedical data into actionable scientific knowledge. Our solutions, including OmicSoft, Discovery Knowledge Base, Ingenuity Pathway Analysis (IPA) and QCI, enable pharmaceutical, biotech, academic and government researchers to interpret molecular and genomic data.

As a Senior Data Scientist – Biomedical Knowledge Graphs, you will own the development, validation and release of biomedical knowledge base products supporting scientists and AI-enabled applications. Working with curated RDF content, knowledge graphs and analytical databases, you will build robust pipelines that transform biological knowledge into graph, analytical and tabular formats. Combining data science, knowledge graph technologies and software engineering, you will also work with AI-extracted relationships and LLM-enabled tools, collaborating with content specialists, bioinformaticians, DevOps and data platform engineers.

Your tasks include

• Owning the end-to-end build and release cycle for biomedical knowledge base products, from transferring curated content to the cloud and running pipelines through to ingestion, deployment and production release.
• Investigating and validating complex biomedical datasets using SPARQL and RDF, Neo4j and Cypher, and SQL, analysing release-to-release changes and identifying significant shifts, inconsistencies or quality issues.
• Developing and maintaining production pipelines that transform curated RDF content into graph databases, analytical datasets and tabular exports, ensuring they remain reliable as schemas and source data evolve.
• Integrating AI-extracted biomedical relationships with curated knowledge and supporting MCP servers and client libraries that enable users and LLM-based applications to interact with the knowledge base.
• Diagnosing and resolving data and pipeline issues, tracing problems to their source and collaborating with content specialists to determine whether changes should be addressed in the source knowledge base or within the build.
• Building and improving well-tested Python and/or Java solutions, automated quality checks, build scripts and CI/CD pipelines using test-driven development, code review and modern software engineering practices.
• Collaborating with bioinformatics, content, DevOps and data platform teams while continuously automating manual processes and improving the reliability, quality and efficiency of knowledge base releases. Triaging failing content tests to decide whether a release can safely proceed will also be part of your role.

Your profile

• MSc or PhD in Data Science, Computer Science, Bioinformatics, Computational Biology or a related discipline, or equivalent relevant professional experience, combined with 5+ years of experience developing production data pipelines, scientific data products or knowledge-based applications.
• Strong programming skills in Python and/or Java, together with solid SQL capabilities and experience writing maintainable, well-tested production code.
• Hands-on experience with knowledge graphs or graph data technologies, particularly RDF and SPARQL and/or Neo4j and Cypher, with an interest in expanding your expertise across these technologies.
• Practical experience with AWS, CI/CD and build automation, using technologies such as Jenkins, Gradle, GitHub Actions or Maven, alongside Git-based source control and code review workflows.
• A methodical approach to data validation, quality assurance and reproducible production processes, with the ability to investigate complex datasets, identify anomalies and improve multi-step workflows.
• Strong communication and collaboration skills, with an interest in working across data science, software engineering and scientific disciplines in an international environment.
• Experience in one or more of the following would be advantageous: biomedical or biological data, genes and pathways, biomedical ontologies, knowledge graphs, NLP or LLM-based applications, MCP servers, R, Python or R package development, Docker, or infrastructure as code using AWS CDK.