Senior AI Data Engineer, Data Products & RAG Foundations

Job Description Agilent   helps laboratories around the world   advance   scientific discovery,   diagnostic s,   and applied market   solutions   through   instruments,   software, consumables,   services,   and deep domain   expertise . About   the role:    As a   Senior   AI Data Engineer, Data Products & RAG Foundations , you will   be   a   data   engineering SME within a cross-functional AI pod, working alongside AI engineers, domain experts, business stakeholders, data owners, and platform teams.

Your role is to build   data   products, pipelines, metadata, and retrieval-ready assets that power AI-enabled business and scientific workflows across the enterprise. Pods do not wait for the   enterprise   data foundation   to be complete; they   help   build   it   through execution . Every   data product   created by the   pod is   designed for governance, reuse , and long-term value, with the   next   consumer   in mind from day one.

Th is   role goes beyond   traditional da ta   engineering. You will work with structured and unstructured data, semantic definitions, quality scoring , lineage, contracts, embeddings, vector search, and retrieval foundations for AI systems. You will   also   leverag e   AI-assisted   techniques, such as metadata generation, entity resolution, and conte nt classification, to create trusted, AI -ready   data products at scale .

You do not need   prior experience with   Agilent’s internal data architecture. We are looking for a strong data engineer who understands data quality, governance, and AI-ready data foundations and   is   excited to help shape the future of enterprise AI at Agilent. What   you will   do:   Data Products & Governance   Build and   maintain   AI-ready   data products and pipelines   for   the pod's use case,   ensuring   appropriate governance ,   lineage, metadata, access controls, and documentation from the start.

Design   data products for reuse, treating every asset as a potential enterprise capability rather than   a   point   integration. Da ta Quality and Trust   Estab lish   d ata quality   standards ,   quality scoring , and model-readiness criteria   that support reliable AI behavior and business outcomes. Ensure   q u a lity issues are identified and addressed before the y impact downstream   AI solutions.

Domain Understanding and Partnership   Partner   with   data owners ,   stewards,   business stakeholders, and IT teams to   establish   trusted   definitions ,   authoritative sources , and domain data models. Ensure AI solutions are   ground ed in validated business meaning   rather than   co nvenience-based access to data . Retrieval and AI Foundations   Design r etrieval foundations   that support AI applications , including   structured and unstructured grounding, vector  search,   graph -based approaches, and semantic enrichment   where   appropriate .

Apply   AI- assisted techniques such as   metadata generation, entity resolution, and content classification   to improve the quality, scalability, and discoverability of   data assets . Eng ineering Delivery and Reuse   Design and implement scalable ingestion, integration, and storage frameworks across cloud and   on-premises   environments. Build reusable data assets, tools, and services that support AI engineers, data scientists, and analytics teams.

Contribute reusable data products, patterns, and documentation back to the broader enterprise ecosystem. ​ ​ What success looks like in   the first year     The pod's use case   is   running   entirely   on   governed, quality-scored data products, with no undocumented   or unsupported data   source s . Multiple   data products   created   by   the pod   have   been adopted, reused, or   identified   for reuse across   additional   AI   or   analytic s   use cases.

Data   q uality signals   are integrated   into AI evaluation and   monitoring   processes ,   influencing