Lead AI Engineer, Knowledge & Semantic Systems

The Lead AI Engineer, Knowledge & Semantic Systems is an individual contributor role focused on designing governed foundational data, knowledge, and retrieval systems that support enterprise AI solutions. This position emphasizes semantic modeling, knowledge graph development, metadata frameworks, and retrieval capabilities for accurate, scalable, and compliant AI-driven insights.

Location and Work Schedule

• Location: Bridgewater, NJ (onsite)
• Hybrid eligibility: Up to 2 days/week telecommuting from home and 3 days/week in the Bridgewater, NJ corporate office

Compensation

• Salary: USD 150,000 - 200,000 per yearly

Role Summary

This role builds and maintains governed semantic and retrieval systems that enable agents and BI to use consistent, certified definitions. Responsibilities include establishing canonical metric definitions, extending a commercial ontology and knowledge graph, enforcing semantic constraints, and operating an end-to-end retrieval stack. The position also partners closely with Applied AI Agents engineers to drive measurable improvements in agent answer accuracy and delivery velocity.

Responsibilities

• Design, build, and maintain a governed semantic layer for commercial metrics, including canonical metric definitions, dimensions, hierarchies, joins, grain, and row- and role-level access policy so agents and BI consume certified definitions.
• Codify commercial metric definitions such as TRx, NRx, NBRx, NC TRx, market share and market basket, decile and segment assignment, and projected versus captured volume, including source system, calculation approach, refresh cadence, and known limitations.
• Arbitrate conflicting metric definitions across brand, field, market access, and finance.
• Implement constraints that prevent semantically misleading queries, such as blending projected and actual volumes, mixing incompatible grains, or computing share across non-comparable sources.
• Design and extend the commercial ontology and knowledge graph, covering ECP, account, affiliation and parent-child hierarchy, payer and plan, formulary status, product, territory and alignment, content asset, and engagement.
• Apply entity resolution across sources used by agents, reconciling prescriber and account identity across prescription, claims, specialty pharmacy, and CRM feeds while maintaining group practice and affiliation structures.
• Maintain taxonomies, controlled vocabularies, and synonym and alias mappings to ensure varied business phrasing resolves consistently to governed concepts.
• Encode temporal validity for territory realignments, formulary changes, affiliation changes, and segment refreshes to support historically correct answers.
• Own the retrieval stack end to end, including chunking strategy, embedding model selection and evaluation, and index configuration and tuning.
• Treat retrieval quality as a measured discipline by building labeled query sets and tracking recall and precision at k, groundedness, and citation accuracy, supported by regression testing.
• Manage reindexing, embedding drift, model migration, and vector infrastructure cost and performance at production scale.
• Expose semantic and retrieval capabilities to agents through well-specified interfaces, including Model Context Protocol (MCP) servers and resources, tool contracts, and structured schemas with disambiguation hints, synonym maps, and worked examples.
• Partner with Applied AI Agents engineers as the primary upstream dependency, working on a shared sprint cadence and contributing to agent answer accuracy and delivery velocity.
• Diagnose grounding failures by determining whether issues originate from definition, entity resolution, retrieval, or model reasoning, and remediate within the layer.
• Operate a federated contribution model by reviewing proposed metrics, entities, and relationships and curating the canonical model to extend without fragmentation.
• Partner with Data Engineering, IT, Privacy, and Compliance to enforce access policy, PDRP and HIPAA minimum-necessary handling, and audit trails at the definition and retrieval layer.
• Document and socialize the model and run enablement so analysts and engineers adopt governed definitions instead of rebuilding them locally.

Requirements

• Bachelor's or Master's degree in Computer Science, Data Engineering, Information Science, Machine Learning, or a related field
• 5+ years of experience in data engineering, analytics, semantic modeling, or knowledge engineering
• Expertise in SQL, dimensional data modeling, and business metric governance
• Hands-on experience with semantic layer tools (e.g., dbt Semantic Layer, MetricFlow, Cube, LookML, AtScale)
• Experience designing and managing knowledge graphs, ontologies, and graph databases (e.g., Neo4j)
• Experience with entity resolution, identity management, and master data concepts
• Experience with vector databases, retrieval systems, and search optimization
• Understanding of LLM-enabled solutions, including RAG, tool calling, structured outputs, and MCP
• Strong Python development skills and software engineering best practices (CI/CD, testing, version control, containerization)
• Experience with cloud data platforms and tools such as Snowflake, Databricks, AWS/Azure, dbt, Airflow, or Dagster
• Knowledge of data governance, security, lineage, and compliance requirements
• Proven ability to collaborate effectively across business and technical teams
• Experience working in Agile environments using Scrum, SAFe, or similar methodologies
• Excellent communication and documentation skills, including the ability to align stakeholders on data definitions and standards

Technologies

• Python, SQL
• Azure, AWS, Databricks, Snowflake
• Knowledge Graphs, Semantic Modeling
• Vector Databases, Retrieval Systems
• dbt Semantic Layer, MetricFlow, Cube, LookML, AtScale
• Neo4j
• LLM-enabled solutions, RAG, tool calling, structured outputs, MCP
• CI/CD, testing, version control, containerization
• dbt, Airflow, Dagster
• Scrum, SAFe, PDRP, HIPAA

Benefits

• Medical, dental, vision insurance
• Disability and life insurance
• 401(k) plan and company match
• Tuition reimbursement program (select degrees)
• Company holidays
• Well-being benefits
• Sick time
• Floating holidays
• Paid vacation
• Short-term and/or long-term incentives

Preferred

• Experience with pharmaceutical commercial data, including prescription, claims, payer, specialty pharmacy, hub, and CRM data
• Familiarity with eye care industry dynamics, including ophthalmology, optometry, and Eye Care Professional (ECP) networks
• Experience with customer master data management (MDM) and HCP/HCO data in life sciences
• Experience with graph databases (e.g., Neo4j) and vector database technologies
• Familiarity with content metadata, classification, and approval workflows
• Experience with data governance, cataloging, lineage, and data observability tools
• Knowledge of healthcare compliance requirements, including HIPAA and FDA promotional regulations
• Experience working in regulated industries with strong audit and compliance standards

Additional Information

• Applicants must be authorized to work for any employer in the U.S. The company is unable to sponsor or take over sponsorship of an employment Visa at this time.