AI Data Engineer for COA Accelerator

IQVIA; Lisboa; Presencial; EUR 45 000 - 75 000; Tempo integral

Resumo da oferta

IQVIA is seeking a Data Engineer to build and maintain data infrastructure powering AI-enabled COA strategies. You will own ingestion, transformation, normalization, and governance across public and proprietary sources, including PDFs, regulatory documents, and publications.

You will develop robust pipelines, OCR, metadata enrichment, and indexing, enabling retrieval-augmented generation. Collaboration with AI, product, and science teams is essential, with focus on data quality, traceability,

Qualificações

• Degree in computer science, data engineering, data science, information systems, bioinformatics, engineering, or a related field.
• Experience designing, building, 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 such as PDFs, slide decks, reports, publications, regulatory files, scientific literature, or knowledge repositories.
• Strong understanding of data cleaning, normalisation, metadata management, document parsing, indexing, lineage, versioning, and auditability.
• Familiarity with data modelling approaches for complex knowledge domains, including scientific, clinical, regulatory, or healthcare content.
• Ability to translate domain expert requirements into practical data structures, metadata models, retrieval-ready content, and maintainable pipelines.
• Strong attention to detail and ability to identify data quality issues that could affect AI outputs, source traceability, or regulatory credibility.
• Ability to collaborate effectively with AI engineers, product managers, COA scientists, software engineers, security stakeholders, legal teams, and commercial teams.
• Strong documentation skills, including ability to document data sources, transformations, lineage, access rules, data quality checks, and known limitations.

Responsabilidades

• Design, build, and maintain data infrastructure that supports IQVIA’s AI-enabled COA strategy and COA Accelerator capabilities.
• Own the ingestion, transformation, normalisation, enrichment, indexing, versioning, and governance of public, proprietary, and client-specific data sources.
• Build ingestion pipelines for structured and unstructured sources, including PDFs, Word documents, slide decks, spreadsheets, databases, APIs, clinical trial registries, regulatory documents, scientific publications, and internal repositories.
• Transform raw source material into standardised, searchable, AI-ready formats that support evidence retrieval, source citation, recommendation generation, and expert review workflows.
• Develop repeatable processes for document parsing, OCR, text extraction, metadata enrichment, chunking, deduplication, versioning, indexing, and quality control.
• Provide technical support to the teams building and maintaining the platform’s core knowledge layer, including COA instrument metadata, instrument versions, translations, modes of administration, usage rights, psychometric evidence, therapeutic area mappings, endpoint usage, regulatory precedent, and related scientific evidence.
• Support integration of public data sources such as clinical trial registries, FDA labels, EMA EPARs, HTA records, scientific literature, FDA guidance, public qualification documents, and other relevant evidence repositories.
• Support ingestion of proprietary internal knowledge, publications, thought leadership, other expert-authored content.
• Prepare data for retrieval-augmented generation workflows through high-quality chunking, embeddings, indexes, metadata filters, and source reference structures.
• Collaborate with AI engineers to improve retrieval precision, recall, relevance, and citation accuracy.
• Implement hybrid retrieval approaches combining semantic search, keyword search, structured database queries, and metadata filtering.
• Maintain traceability between AI-generated outputs and source documents.
• Implement data quality controls to identify incomplete, outdated, duplicated, poorly parsed, incorrectly tagged, or otherwise unreliable content.
• Maintain audit trails for source ingestion, transformation, updates, deletions, access rights, and downstream use.
• Work with legal, security, compliance, product, and domain stakeholders to ensure data use aligns with contractual, licensing, privacy, intellectual property, and governance requirements.
• Collaborate across AI Engineering, Product, COA Science and Software Engineering.

Conhecimentos

Python

SQL

APIs

ETL/ELT

Data pipelines

Cloud platforms

Documentation

Formação académica

Degree in computer science or related field

Ferramentas

Elasticsearch/OpenSearch

Azure

AWS

GCP

Descrição da oferta de emprego

IQVIA is seeking a Data Engineer to build and maintain data infrastructure powering AI-enabled COA strategies. You will own ingestion, transformation, normalization, and governance across public and proprietary sources, including PDFs, regulatory documents, and publications.

You will develop robust pipelines, OCR, metadata enrichment, and indexing, enabling retrieval-augmented generation. Collaboration with AI, product, and science teams is essential, with focus on data quality, traceability,