Data Governance Specialist

We are looking for a Senior Neo4j Graph Data Engineer to design and implement graph-based analytics solutions supporting fraud detection, Anti-Money Laundering and financial-crime investigations. The successful candidate will model complex banking relationships in Neo4j, apply Graph Data Science algorithms, develop investigation dashboards and collaborate with Risk, AML, Compliance and Data Science teams to identify suspicious activities and interconnected fraud networks. Key Responsibilities Design and implement Neo4j graph data models covering customers, accounts, transactions, devices and their interconnected relationships. Develop and optimise Cypher queries for complex relationship analysis and fraud investigations. Apply Neo4j Graph Data Science algorithms, including:Community DetectionLink PredictionNode EmbeddingsCentrality AnalysisPathfinding Use algorithms such as Louvain, Label Propagation, Node2Vec and GraphSAGE to identify suspicious networks and hidden fraud patterns. Build Python-based ETL pipelines for data ingestion, processing and integration with Neo4j. Develop interactive investigation dashboards and graph visualisations using Neo4j Bloom. Partner with Risk Management, AML, Compliance and Data Science teams to translate business requirements into scalable technical solutions. Support real-time fraud detection through integration with data-streaming technologies. Optimise graph database indexing, queries, storage and performance for production workloads. Ensure the scalability, reliability and availability of Neo4j environments. Maintain technical documentation, operational procedures and solution-design materials. Monitor emerging graph technologies and recommend improvements to the bank’s fraud-analytics capabilities. Must-Have Requirements Five to six years of overall IT experience. At least two years of hands-on experience with Neo4j, Cypher and the Graph Data Science library. Strong Python skills for ETL pipelines, data processing and Neo4j integration. Strong understanding of graph data modelling, indexing, query optimisation and performance tuning. Practical experience with graph algorithms, including community detection, link prediction, node embeddings, centrality measures and pathfinding. Experience with Neo4j Bloom or similar graph-visualisation tools. Strong analytical and problem-solving capabilities. Ability to translate fraud, AML and compliance requirements into technical solutions. Strong communication and stakeholder-management skills. Good-to-Have Requirements Experience in banking, fraud detection, AML, KYC or financial-crime compliance. Experience with Amazon Neptune, TigerGraph, JanusGraph or other graph databases. Knowledge of scikit-learn, TensorFlow or PyTorch. Experience integrating machine-learning models with graph analytics. Familiarity with AWS, Microsoft Azure or Google Cloud Platform. Experience deploying and operating Neo4j in cloud environments. Knowledge of Kafka, Amazon Kinesis or similar streaming technologies. Experience with CI/CD, Terraform, CloudFormation and DevOps practices. Neo4j Certified Professional or Graph Data Science certification.