Senior AI Data Engineer, Data Products & RAG Foundations

Agilenthelps laboratories around the worldadvancescientific discovery,diagnostics,and applied marketsolutionsthroughinstruments,software, consumables,services,and deep domainexpertise.

Aboutthe role

As aSeniorAI Data Engineer, Data Products & RAG Foundations, you willbeadataengineering SME within a cross-functional AI pod, working alongside AI engineers, domain experts, business stakeholders, data owners, and platform teams.Your role is to builddataproducts, pipelines, metadata, and retrieval-ready assets that power AI-enabled business and scientific workflows across the enterprise.

Pods do not wait for theenterprisedata foundationto be complete; theyhelpbuilditthrough execution.Everydata productcreated by thepod isdesigned for governance, reuse, and long-term value, with thenextconsumerin mind from day one.

Thisrole goes beyondtraditional dataengineering.You will work with structured and unstructured data, semantic definitions, quality scoring, lineage, contracts, embeddings, vector search, and retrieval foundations for AI systems. You willalsoleverageAI-assistedtechniques, such as metadata generation, entity resolution, and content classification, to create trusted, AI-readydata products at scale.

You do not needprior experience withAgilent's internal data architecture.We are looking for a strong data engineer who understands data quality, governance, and AI-ready data foundations andisexcited to help shape the future of enterprise AI at Agilent.

Whatyou willdo

Data Products & Governance

• Build andmaintainAI-readydata products and pipelinesforthe pod's use case,ensuringappropriate governance,lineage, metadata, access controls, and documentation from the start.

• Designdata products for reuse, treating every asset as a potential enterprise capability rather thanapointintegration.

Data Quality and Trust

• Establishdata qualitystandards,quality scoring, and model-readiness criteriathat support reliable AI behavior and business outcomes.

• Ensurequality issues are identified and addressed before they impact downstreamAI solutions.

Domain Understanding and Partnership

• Partnerwithdata owners,stewards,business stakeholders, and IT teams toestablishtrusteddefinitions,authoritative sources, and domain data models.

• Ensure AI solutions aregrounded in validated business meaningrather thanconvenience-based access to data.

Retrieval and AI Foundations

• Design retrieval foundationsthat support AI applications, includingstructured and unstructured grounding, vector search,graph-based approaches, and semantic enrichmentwhereappropriate.

• ApplyAI-assisted techniques such asmetadata generation, entity resolution, and content classificationto improve the quality, scalability, and discoverability ofdata assets.

Engineering Delivery and Reuse

• Design and implement scalable ingestion, integration, and storage frameworks across cloud andon-premisesenvironments.

• 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 inthe first year

• The pod's use caseisrunningentirelyongoverned, quality-scored data products, with no undocumentedor unsupported datasources.

• Multipledata productscreatedbythe podhavebeen adopted, reused, oridentifiedfor reuse acrossadditionalAIoranalyticsuse cases.

• Dataquality signalsare integratedinto AI evaluation andmonitoringprocesses,influencingAIbehavior andoutcomes.

• Data-to-build timehas measurablyimproved throughreuse, automation,and process optimization.

Technical Expertise

• Strong data engineeringexperiencebuilding AI-ready data products, not justwarehouse tables and dashboards.

• Hands-on familiarity withplatformssuch asMicrosoftFabric, Snowflake, vector databases,graphstores, andoperatingunder data contracts, lineage, and certification requirements.

• Experience with RAGfoundations, includingchunking, embedding, hybrid retrieval, andunderstanding howretrievalqualityimpactsagent/ AIbehaviorand outcomes.

DomainandProduct Mindset

• Adisposition to workwithina business domain, partnering withdatastewardsand subject matter expertsto understandthe meaning behind the data.

• Aninstinct to build for reuse,creatingassetsintended forsecondconsumersand usecases,not just the first.

CommunicationandInfluence

• Excellent communication and the ability to influencetechnical andnon-technical audiences.

• Able to build trustedpartnershipswith domain experts, stewards, business stakeholders andfunctionssuch asLegal, Quality, and Security.

CuriosityandGrowth Mindset

• Curiosity about AI, itsopportunities,limitations, stayinginformedaboutemerging approaches, whilemaintaininga healthyskepticismand focus on responsible implementation.

• A lifelong learnerwho continuously adapts skillsandways of working in a rapidly evolving field.

Education andSeniority

• Bachelor's orMaster'sdegreein Computer Science,Engineering, Information Systems, Data Science, or a related field,or equivalentpractical experience.

• Typically, at least 8+ yearsofrelevant experience for entry to this level.