We are looking for a Senior Knowledge Graph Engineer with strong, hands-on expertise in Neo4j, graph data modelling, advanced Cypher, document intelligence and NLP-based information extraction. The selected candidate will design and build production-grade knowledge graphs that support GraphRAG, recommendation systems and other enterprise AI applications.

Key Responsibilities :

- Document Intelligence and Extraction : Develop and scale automated ingestion and extraction pipelines to process unstructured and semi-structured documents, including PDFs, reports and contracts, using modern NLP, OCR and Large Language Model frameworks.

- Knowledge Graph Architecture : Design robust ontologies and graph data models for Neo4j, ensuring effective schema design for complex domain entities and relationships.

- Pipeline Engineering : Implement Named Entity Recognition, relation extraction, entity resolution and data-disambiguation workflows to ensure the accuracy and consistency of extracted information.

- Database Optimization : Develop, tune and optimize complex Cypher queries. Use Neo4j Graph Data Science algorithms to support applications such as GraphRAG and recommendation systems.

- Data Integration : Build end-to-end pipelines that integrate Neo4j with vector databases, relational databases, APIs and other enterprise data sources.

- Data Governance and Quality : Establish validation frameworks to monitor data quality, graph consistency, relationship integrity and schema evolution.

- Collaboration : Work closely with ML engineers, data engineers and software developers to integrate graph-based data and insights into production-grade enterprise products.

Required Qualifications and Technical Skills :

- Experience : 6+ years of overall experience in software engineering, data engineering, knowledge engineering or NLP-focused development, including a minimum of 3 years of deep, hands-on production experience with Neo4j.

- Graph Databases : Strong expertise in Neo4j, graph data modelling, schema design, indexing and performance optimization.

- Cypher : Advanced proficiency in writing, profiling and optimizing complex Cypher queries.

- Data Extraction and NLP : Strong experience extracting structured information from unstructured text using NLP, OCR, Python libraries and LLM orchestration frameworks such as LangChain.

- Knowledge Engineering : Hands-on experience with ontologies, Named Entity Recognition, relation extraction, entity resolution and data disambiguation.

- Programming : Advanced proficiency in Python and experience with data-processing libraries such as Pandas and NumPy.

- Pipeline Architecture : Experience designing and building end-to-end data ingestion, transformation and graph-loading pipelines.

- Integration : Experience integrating graph databases with vector databases, relational data stores and enterprise applications.

- Production Experience : Demonstrated experience deploying, optimizing and supporting Neo4j-based solutions in production environments.

Preferred Qualifications :

- Hands-on experience implementing GraphRAG architectures.

- Experience with Neo4j Graph Data Science.

- Experience with vector search, embeddings and hybrid graph-vector retrieval.

- Familiarity with Microsoft Azure.

- Experience with Docker and Kubernetes.