Senior Data Engineer: Biomedical AI & Multi-Omics

Boehringer Ingelheim Pharmaceuticals, Inc.; Greater London, Aberdeen City; Hybrid; GBP 90.000 - 120.000; Vollzeit

Benefits dieser Stelle

Hybrid work (3 days in office)

Zusammenfassung

Boehringer Ingelheim Pharmaceuticals, Inc. is hiring two Senior Data Engineers in London for AI Enablement within Computational Innovation.

The role focuses on building robust data pipelines to transform harmonised biomedical datasets into AI-ready assets across multi-omics, clinical and imaging domains. You will own significant data engineering workstreams and enable model training, fine-tuning and inference in production.

Qualifikationen

• PhD in ML, CS, Bioinformatics, Computational Biology or related field
• Strong hands-on data engineering for ML
• Experience with medical imaging or multi-omics data
• Practical experience with entity linking in biomedical/clinical contexts
• Familiarity with data governance and Trusted Research Environments

Aufgaben

• Build and maintain entity linking pipelines connecting patients, samples and biomedical entities across modalities
• Build and maintain cross-modal integration pipelines for imaging, multi-omics and clinical records
• Ensure pipelines comply with data access permissions and consent conditions in controlled environments
• Create biomedical benchmark datasets with versioning and documentation
• Write clean, well-tested, well-documented code and participate in code reviews
• Stay current with advances in data engineering for biomedical AI

Ausbildung

PhD in Machine Learning / Computer Science / Bioinformatics / Computational Biology

Data engineering for machine learning

Imaging or multi-omics data experience

Entity linking experience

Data governance / Trusted Research Environments

Jobbeschreibung

Boehringer Ingelheim Pharmaceuticals, Inc. is hiring two Senior Data Engineers in London for AI Enablement within Computational Innovation.

The role focuses on building robust data pipelines to transform harmonised biomedical datasets into AI-ready assets across multi-omics, clinical and imaging domains. You will own significant data engineering workstreams and enable model training, fine-tuning and inference in production.