Remote AI Data Engineer for COA Knowledge Platform

IQVIA LLC; Madrid; Presencial; EUR 55.000 - 80.000; Jornada completa

Descripción de la vacante

IQVIA’s COA team is seeking a Data Engineer to transform fragmented clinical, regulatory, and scientific content into structured, AI-ready knowledge assets powering AI-enabled COA workflows. You will design robust ingestion pipelines, governance, and metadata enrichment to support evidence retrieval and expert review across global clients.

Join a collaborative, multi-disciplinary team and contribute to scalable data solutions that underpin COA research and strategy.

Formación

• Degree in a technical field (computer science, data engineering, etc.).
• Experience designing and maintaining data pipelines for structured and unstructured data.
• Strong Python and SQL skills.
• Experience with APIs, relational databases, document stores, search indexes, cloud data platforms, and ETL/ELT workflows.
• Experience handling large volumes of text-heavy documents (PDFs, reports, literature).
• Strong understanding of data cleaning, normalisation, metadata management, document parsing, indexing, lineage, versioning, and auditability.
• Familiarity with data modelling for scientific, clinical, regulatory, or healthcare content.
• Ability to translate domain requirements into practical data structures and retrieval-ready content.
• Strong attention to data quality and source traceability.
• Ability to collaborate with AI engineers, product managers, scientists, software engineers, and legal/commercial teams.
• Experience with life sciences data preferred.
• Fluency in English.

Responsabilidades

• Design, build, and maintain data infrastructure that supports IQVIA’s AI-enabled COA strategy and COA Accelerator capabilities.
• Own ingestion, transformation, normalisation, enrichment, indexing, versioning, and governance of data sources.
• Build ingestion pipelines for structured and unstructured sources including PDFs, documents, databases, APIs, and publications.
• Transform raw material into standardised, searchable, AI-ready formats supporting retrieval and citation workflows.
• Develop repeatable processes for parsing, OCR, metadata enrichment, chunking, deduplication, versioning, indexing, and quality control.
• Provide technical support to teams building the platform’s knowledge layer, including instrument metadata and regulatory evidence.
• Support integration of public data sources such as clinical trial registries, FDA/EMA data, HTA, literature.
• Support ingestion of proprietary internal knowledge and publications.
• Prepare data for retrieval-augmented generation with robust chunking and indexing.
• Collaborate with AI engineers to improve precision, recall, and citation accuracy.
• Maintain audit trails and data quality controls across ingestion and transformations.
• Ensure data-use aligns with governance, licensing, and privacy requirements.
• Collaborate across AI Engineering, Product, COA Science and Software Engineering.

Conocimientos

Python

SQL

APIs

ETL/ELT

OCR

Text processing

Data cleaning

Metadata management

Indexing

Versioning

Governance

Documentation

Collaboration

English fluency

Educación

Degree in computer science, data engineering, data science, information systems, bioinformatics, computational biology, engineering, or related field

Herramientas

Elasticsearch/OpenSearch

Azure AI Search

Pinecone

Weaviate

Milvus

Qdrant

Cloud data platforms (Azure/AWS/GCP)

Descripción del empleo

IQVIA’s COA team is seeking a Data Engineer to transform fragmented clinical, regulatory, and scientific content into structured, AI-ready knowledge assets powering AI-enabled COA workflows. You will design robust ingestion pipelines, governance, and metadata enrichment to support evidence retrieval and expert review across global clients.

Join a collaborative, multi-disciplinary team and contribute to scalable data solutions that underpin COA research and strategy.