Senior Data Engineer, AI Data Products

Alternate Locations: Radnor, PA (Pennsylvania); Charlotte, NC (North Carolina); Fort Wayne, IN (Indiana); Greensboro, NC (North Carolina)     Work Arrangement: Hybrid : Employee will work 3 days a week in a Lincoln office   Relocation assistance:   is not available for this opportunity.   Requisition #:  76678   The Role at a Glance

Lincoln Financial's AI, Data and Analytics (AIDA) organization is building the capabilities required for an AI-enabled business. Within AIDA, Data Strategy & Governance turns priority insurance and retirement use cases into governed, reusable data products and services. We work backward from the decisions and actions AI agents and applications must support, then build the common meaning, quality, metadata, lineage, and secure access needed to trust the result. We deliver with AIDA's infrastructure, platform, engineering, MLOps, and AI-native platform teams, with governance built into the product.   As a Senior Data Engineer, you wil lead the end-to-end technical direction and delivery of complex AI-ready data products. You will connect priority business and AI use cases to the data capabilities beneath them, including shared meaning, rules, quality, lineage, secure access, and reusable services. You will also lead hands-on graph and GraphRAG delivery where relationships and unstructured knowledge matter, while choosing simpler relational, search, or rules-based patterns when they fit better. What you'll be doing

Lead discovery with business and product owners, domain experts, stewards, source owners, and partner AIDA pillars to define the questions, actions, outcomes, product boundaries, and accountable owners. Design the product's canonical and consumer models, ontology and semantic layer, business rules, contracts, interfaces, quality controls, metadata, lineage, provenance, and secure access. Design and build graph models in Amazon Neptune or comparable technology, including entities, relationships, effective dates, rules, provenance, SPARQL queries, and performance tuning. Implement GraphRAG and hybrid graph-vector retrieval, including ingestion, entity and relationship extraction, embeddings, graph enrichment, filtering, retrieval, reranking, grounding, and citations. Design and build AWS source-to-product pipelines and agent-facing APIs or Model Context Protocol interfaces using fit-for-purpose lakehouse, orchestration, transformation, and infrastructure-as-code patterns. Evaluate graph, relational, vector, search, and rules-based approaches against representative questions, expected evidence, answer quality, latency, security, operational complexity, and cost. Lead a blended delivery pod through production readiness, code and design review, incident prevention, partner knowledge transfer, and reusable patterns that avoid unnecessary complexity and lock-in. What we’re looking for

A bachelor's degree or equivalent work experience, plus typically 5 or more years of relevant experience with ownership of complex production data systems or products. Substantial hands-on experience building and operating graph solutions with Amazon Neptune or comparable technology, including graph modeling, SPARQL, query analysis, and performance tuning. Hands-on implementation of GraphRAG or comparable hybrid graph-vector retrieval, including ingestion, embeddings, retrieval, reranking, grounding, and citations. Advanced Python and SQL, plus strong AWS data-platform experience, orchestration, data modeling, distributed processing, automated testing, CI/CD, and infrastructure as code. Proven ability to translate a business capability into semantics, rules, contracts, controls, interfaces, and measurable evaluations, and to lead architecture decisions through influence while contributing hands-on. Ownership of quality, lineage, privacy, access, observability, recovery, and production operations for sensitive or regulated data.

Nice to