Director, AI Native Analytics

Lincoln Financial • Radnor, PA

1d • Hybrid

About The Position

Lincoln Financial Group is building an AI Native Intelligence platform that turns enterprise data into a conversational, agentic layer for business users. The platform includes an AWS-native ingestion and extraction pipeline, a governed semantic layer and business knowledge graph, and an intelligence layer that answers questions in plain language and proactively surfaces changes in enterprise data.

The role is described as the hands-on builder of the platform’s conversational and analytical experience, designing and shipping Bedrock agents, retrieval pipelines, pattern-detection logic, and natural-language-to-analytics capabilities. It is an individual-contributor-heavy, deeply technical position focused on architecture, prompts, and code, in close partnership with the Senior Director and business stakeholders. The role also provides technical direction and mentorship to engineers contributing to the conversational AI workstream.

The position is hybrid, with employees working three days per week in a Lincoln office. Alternate locations are Radnor, Pennsylvania; Charlotte, North Carolina; Fort Wayne, Indiana; and Greensboro, North Carolina. Relocation assistance is not available. Applications are accepted through January 30, 2026, subject to earlier closure.

Requirements

• At least 8 years of experience in Data Analytics or Business Intelligence, including at least 2 years building production LLM-based analytics systems.
• Production-level hands-on expertise with the AWS AI/data stack, including Amazon Bedrock Knowledge Bases and Agents/AgentCore, AWS Lambda, Step Functions, Amazon S3, AWS Glue, and Amazon Athena.
• Working experience with a vector store such as OpenSearch Serverless or similar.
• Practical prompt-engineering and LLM application-development skills, including structured extraction, tool-calling or agentic patterns, retrieval design, and iterative evaluation against real questions.
• Understanding of semantic layers, business ontologies, or metrics layers, and how to ground LLM outputs in governed business definitions.
• Experience building or applying pattern-, trend-, or anomaly-detection techniques over enterprise data and turning findings into actionable information for business users.
• Strong proficiency in Python and/or TypeScript/Node.js for building extraction pipelines, agent tools, and integration code.
• Working knowledge of SQL and cloud analytics engines such as Athena or Redshift, sufficient to design and validate natural-language-to-SQL experiences.
• Clear communication skills, including the ability to demonstrate a working system to engineers and explain its behavior and limitations to nontechnical business stakeholders.
• Bachelor’s degree in Computer Science, Engineering, or a related field, or equivalent practical experience.

Nice To Haves

• Experience with GraphRAG or other knowledge-graph-grounded retrieval patterns and a graph database such as Amazon Neptune.
• Experience with a semantic-layer or metrics-layer tool such as Cube.dev used to serve consistent metrics to BI and AI consumers.
• Experience with NLP or document-processing pipelines, such as Amazon Comprehend, for extracting structure from varied unstructured enterprise data.
• Experience in insurance, financial services, or another regulated industry, with a working understanding of PII handling and data privacy or compliance considerations.
• Experience configuring LLM safety or evaluation tooling such as Bedrock Guardrails, or building an evaluation harness for generative AI systems.
• Familiarity with enterprise data domains such as financial, operational, customer, or workforce data within a large organization.

Responsibilities

• Design and build the conversational AI experience, including Bedrock Agents through AgentCore or MCP/API, retrieval-augmented generation over Bedrock Knowledge Bases or OpenSearch Serverless, natural-language-to-SQL over Athena, and knowledge-graph relationship queries using Amazon Neptune or GraphRAG.
• Build capabilities that detect patterns, trends, and anomalies across enterprise data and proactively surface notable findings.
• Build and tune an AI extraction pipeline that converts unstructured data such as documents, logs, notes, and communications into structured, query-ready facts using Amazon Comprehend and/or LLM-based extraction through the Bedrock Converse API, Lambda, Step Functions, and DynamoDB.
• Own prompt engineering and agent tool design, including system instructions, tool/action-group definitions, structured-output schemas, and model selection or tiering to balance accuracy, latency, and cost.
• Integrate the conversational layer with the platform’s semantic layer and business ontology so answers align with governed KPI definitions, metrics, and business rules.
• Build evaluation and quality processes for LLM-based systems, including golden question sets, retrieval and accuracy scoring, hallucination and abstention testing, and regression checks before releases.
• Implement AI guardrails with security and compliance partners, including PII detection and redaction, Bedrock Guardrails configuration, access-controlled data zones, and audit logging for AI-generated answers.
• Partner with enterprise business stakeholders to translate real questions into conversational and pattern-detection features and iterate based on usage and accuracy feedback.
• Mentor and provide technical direction to engineers contributing to the conversational AI workstream, and represent the workstream in architecture reviews led by the Senior Director.
• Monitor developments in the AWS AI landscape, including Bedrock models, AgentCore, retrieval, and evaluation tooling, and bring recommendations to the team.

Benefits

• Clearly defined career tracks and job levels, with associated behaviors for Lincoln’s core values and leadership attributes
• Leadership development and virtual training opportunities
• PTO and parental leave
• Competitive 401(k) and employee benefits
• Free financial counseling, health coaching, and employee assistance program
• Tuition assistance program
• Flexible work arrangements
• Productivity and technology tools and training
• The role may be eligible for the discretionary Annual Incentive Program; other rewards may include long-term incentives and sales incentives

What This Job Offers

• Job Type: Full-time
• Career Level: Director