Senior Knowledge Graph Engineer

Senior Knowledge Graph Engineer

Role Overview

We are seeking a senior hands-on engineer to design, build, and productionize knowledge graph and semantic data systems for enterprise AI use cases in a regulated financial services environment.

This role will focus on graph databases, ontology implementation, entity resolution, relationship modeling, provenance, and integration of structured and unstructured data into graph-enabled intelligence workflows. The core need is a senior engineer who can assess technical tradeoBs, build durable systems, and turn early graph / ontology concepts into working infrastructure.

Core Responsibilities

• Design and build knowledge graph systems supporting company, issuer, investor, transaction, document, and market-intelligence use cases.
• Implement graph data models, ontology structures, entity types, canonical identifiers, relationship predicates, provenance, and temporal attributes.
• Develop entity resolution, deduplication, canonicalization, and relationshipnormalization pipelines across structured and unstructured data sources.
• Build ingestion and transformation workflows that convert documents, source data, and extracted facts into graph-ready representations.
• Evaluate and implement graph database technologies, including tradeoBs across property graph, RDF / OWL, relational, and hybrid approaches.
• Integrate graph systems with internal data platforms, APIs, AI extraction / validation workflows, and downstream application surfaces.
• Define validation, confidence scoring, quarantine, and human-review workflows for graph assertions.
• Create technical design documents, data model specifications, implementation plans, and operational documentation.
• Partner with applied AI, data, product, engineering, and business stakeholders to move graph-enabled capabilities from prototype to production.

Critical Skills

• Deep hands-on experience with knowledge graphs, graph databases, ontology implementation, semantic data modeling, and entity resolution.
• Strong engineering experience with data pipelines, APIs, backend systems, and production integration patterns.
• Practical experience with graph technologies such as Neo4j, Amazon Neptune, TigerGraph, Stardog, RDF / OWL, SPARQL, Cypher, or similar.
• Strong understanding of canonical IDs, entity matching, relationship modeling, provenance, temporal data, data lineage, and graph quality controls.
• Familiarity with LLM-based extraction, classification, normalization, retrieval, or validation workflows.
• Strong Python, data engineering, and backend development skills.
• Ability to operate independently in ambiguity and produce clear technical documentation.

Preferred Background

• Experience building graph or semantic data systems for financial services, market intelligence, enterprise search, compliance, risk, research, or other complex entity / relationship domains.
• Experience integrating structured data, documents, web content, and third-party data into graph-based systems.
• Experience with human-in-the-loop validation, data quality workflows, source attribution, and auditability.
• Experience working with cloud data environments, enterprise data platforms, and AI enabled analytics systems.

Success Profile

The ideal candidate can take a complex real-world domain, define the core entities and relationships, and engineer a graph-backed system that is accurate, traceable, maintainable, and useful. Success in this role means turning early graph / ontology concepts into production oriented infrastructure that supports entity resolution, relationship intelligence, source backed evidence, temporal facts, and AI-enabled enterprise intelligence workflows.