Lead AI Engineer (Knowledge Graph / Ontology & Agentic AI)

Job Description Lead AI Engineer (Knowledge Graph / Ontology & Agentic AI)

Location: Dallas, TX

Role Summary

Seeking a Lead AI Engineer with strong expertise in Knowledge Graph (KG), Ontology modeling, and Generative AI (LLMs, Agentic AI) to design and scale a Customer Knowledge Graph platform using Neo4j and App Orchid. The role will lead AI product/platform development, enabling relationship intelligence, Customer 360 insights, and AI-driven decisioning.

Key Responsibilities

Knowledge Graph & Ontology (Neo4j / App Orchid)

• Design and implement ontology models and semantic frameworks
• Build and scale Customer Knowledge Graph using Neo4j and App Orchid
• Develop entity resolution, relationship mapping, and enrichment pipelines
• Write and optimize graph queries (Cypher) for analytics and insights
• Manage performance, scalability, and governance of KG platform

AI & Agentic AI Development

• Architect and implement Agentic AI and multi-agent systems
• Leverage LLMs and RAG with Knowledge Graph for contextual intelligence
• Enable capabilities such as:
• Customer 360 insights
• Relationship discovery & scoring
• Natural language querying (Graph/SQL agents)
• Drive end-to-end AI lifecycle (design deploy optimize)

Data Engineering & Integration

• Build scalable pipelines to integrate enterprise data into KG
• Implement customer identity resolution and data quality frameworks
• Design APIs for application and AI model integration

Leadership & Platform Ownership

• Lead AI platform architecture and roadmap
• Mentor engineering teams and enforce best practices
• Drive AI-first SDLC adoption and enterprise scaling
• Collaborate with business, data science, and engineering stakeholders

Required Skills

• Knowledge Graph & Ontology: RDF, OWL, semantic modeling
• Graph Platforms: Strong hands-on with Neo4j and App Orchid
• Graph Querying: Cypher (mandatory)
• AI/GenAI: LLMs, RAG, Agentic AI (CrewAI/LangGraph)
• Programming: Python (AI + data engineering)
• Data Engineering: Spark, Kafka, Airflow (or equivalent)
• Cloud: AWS / Azure
• MLOps/DevOps: CI/CD, scalable system design

Preferred Skills

• Customer 360 / Customer Data Platforms
• Graph analytics (community detection, centrality)
• Graph visualization tools
• Exposure to GNNs
• Docker / Kubernetes

Leadership Expectations

• Own AI product/platform delivery end-to-end
• Define technical roadmap and architecture strategy
• Drive enterprise AI adoption with business impact (revenue, engagement)