Senior AI Data Engineer, Data Products & RAG Foundations

Agilent helps laboratories around the world advance scientific discovery, diagnostics, and applied market solutions through instruments, software, consumables, services, and deep domain expertise. 

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.   

This role goes beyond traditional data 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 leverage AI-assisted techniques, such as metadata generation, entity resolution, and content classification, to create trusted, AI-ready data products at scale.   

• 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.  

• Establish data quality standards, quality scoring, and model-readiness criteria that support reliable AI behavior and business outcomes. 

• Ensure quality issues are identified and addressed before they impact downstream AI solutions.   

• Partner with data owners, stewards, business stakeholders, and IT teams to establish trusted definitions, authoritative sources, and domain data models. 

• Ensure AI solutions are grounded in validated business meaning rather than convenience-based access to data.  

• Design retrieval 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.  

• 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 sources.  

• Multiple data products created by the pod have been adopted, reused, or identified for reuse across additional AI or analytics use cases.  

• Data quality signals are integrated into AI evaluation and monitoring processes, influencing AI behavior and outcomes.  

• Data-to-build time has measurably improved through reuse, automation, and process optimization. 

• Strong data engineering experience building AI-ready data products, not just warehouse tables and dashboards.  

• Hands-on familiarity with platforms such as Microsoft Fabric, Snowflake, vector databases, graph stores, and operating under data contracts, lineage, and certification requirements.  

• Experience with RAG foundations, including chunking, embedding, hybrid retrieval, and understanding how retrieval quality impacts agent/ AI behavior and outcomes.  

• A disposition to work within a business domain, partnering with data stewards and subject matter experts to understand the meaning behind the data. 

• An instinct to build for reuse, creating assets intended for second consumers and use cases, not just the first. 

• Excellent communication and the ability to influence technical and non-technical audiences. 

• Able to build trusted partnerships with domain experts, stewards, business stakeholders and functions such as Legal, Quality, and Security. 

• Curiosity about AI, its opportunities, limitations, staying informed about emerging approaches, while maintaining a healthy skepticism and focus on responsible implementation.  

• A lifelong learner who continuously adapts skills and ways of working in a rapidly evolving field.  

• Bachelor’s or Master’s degree in Computer Science, Engineering, Information Systems, Data Science, or a related field, or equivalent practical experience. 

• Typically, at least 8+ years of relevant experience for entry to this level.