Senior AI Data Engineer: Data Products & RAG Foundations

Agilent Technologies; Barcelona; Presencial; EUR 90.000 - 135.000; Jornada completa

Descripción de la vacante

Agilent Technologies in Barcelona seeks a Senior AI Data Engineer to build AI-ready data products and pipelines, grounding data with semantic definitions and contracts. The role blends data engineering with AI governance, quality scoring, and agent-enabled curation to scale data delivery across the platform.

You will collaborate with data owners, stewards, and IT to ground pod data in reliable sources, drive improvements in data-to-build time, and contribute to reusable data assets for

Formación

• 8+ years of relevant experience in data engineering or AI data platforms.
• Ability to define semantic data definitions and contracts.
• Experience with data lineage and certification requirements.

Responsabilidades

• Build domain data products and pipelines aligned with AI-ready standards.
• Develop retrieval foundations (structured/unstructured grounding, embeddings).
• Collaborate with data owners, stewards, and IT to ground pod data in reliable sources.
• Apply AI-driven curation and contribute outputs to the data registry.
• Design data collection frameworks for large-scale ingestion and scalable platforms.

Conocimientos

Data engineering

AI-ready data products

RAG foundations

Microsoft Fabric

Snowflake

Embeddings

Vector stores

Graph stores

Educación

Bachelor's or Master's Degree

Herramientas

Microsoft Fabric

Snowflake

Vector stores

Graph databases

RAG tooling

Descripción del empleo

Agilent Technologies in Barcelona seeks a Senior AI Data Engineer to build AI-ready data products and pipelines, grounding data with semantic definitions and contracts. The role blends data engineering with AI governance, quality scoring, and agent-enabled curation to scale data delivery across the platform.

You will collaborate with data owners, stewards, and IT to ground pod data in reliable sources, drive improvements in data-to-build time, and contribute to reusable data assets for