Data Engineer
Summary
Designs and implements Neo4j graph databases to model banking relationships and detect fraud patterns using graph analytics, building real-time investigation tools for financial crime prevention.
Job Description
Role Summary
Join Team to build innovative Neo4j-powered solutions that detect fraud rings, money laundering networks, and account takeovers in real-time. You'll work at the intersection of data science, graph analytics, and financial crime prevention—helping our clients in the banking sector safeguard their operations and protect their customers.
Key Responsibilities
- Model Complex Banking Data in Neo4j: Design and implement graph data models representing customers, accounts, transactions, devices, and their interconnected relationships.
- Apply Graph Data Science (GDS) Algorithms: Leverage Community Detection, Link Prediction, Node Embeddings, and Pathfinding algorithms to uncover hidden fraud patterns and suspicious networks.
- Build Real-Time Investigation Dashboards: Develop interactive visualisations using Neo4j Bloom to empower Risk and AML teams with actionable insights.
- Collaborate Across Teams: Partner closely with Risk Management, Anti-Money Laundering (AML), Compliance, and Data Science teams to translate business requirements into technical solutions that reduce fraud losses.
- Optimise Performance: Ensure scalability, performance tuning, and reliability of graph databases in production environments.
- Drive Innovation: Stay current with emerging graph technologies and fraud detection techniques, and contribute to continuous improvement of our analytics capabilities.
Qualifications
Must-Have
- 5–6 years of overall IT experience, with 2+ years of hands-on experience working with Neo4j, Cypher query language, and Graph Data Science (GDS) library.
- Strong proficiency in Python for ETL pipelines, data processing, and integration with Neo4j GDS workflows.
- Solid understanding of graph database concepts, including data modelling, indexing, query optimisation, and performance tuning.
- Experience applying GDS algorithms such as Community Detection (Louvain, Label Propagation), Link Prediction, Node Embeddings (Node2Vec, GraphSAGE), and Centrality measures.
- Familiarity with Neo4j Bloom or similar graph visualisation tools for building investigative dashboards.
- Experience in the Banking, Fraud Detection, or AML domain is highly preferred.
- Strong analytical and problem-solving skills with the ability to translate complex business requirements into technical solutions.
- Excellent communication and collaboration skills to work effectively with cross-functional teams.
Good-to-Have
- Experience with other graph databases (e.g., Amazon Neptune, TigerGraph, JanusGraph).
- Knowledge of machine learning frameworks (e.g., scikit-learn, TensorFlow, PyTorch) and integrating ML models with graph analytics.
- Familiarity with cloud platforms (AWS, Azure, GCP) and deploying Neo4j in cloud environments.
- Understanding of data streaming technologies (Kafka, Kinesis) for real-time fraud detection pipelines.
- Experience with CI/CD pipelines, Infrastructure as Code (Terraform, CloudFormation), and DevOps practices.
- Knowledge of regulatory frameworks related to AML, KYC, and financial crime compliance.
- Neo4j Certified Professional or Graph Data Science certification is a plus.
Qualifications:
- Bachelor's or Master's degree in Computer Science, Data Science, Information Technology, or a related field.
- 5-6 years of experience in IT production, preferably in banking or financial services
- Good problem-solving skills and ability to work under pressure in a fast-paced environment.
- Strong communication skills with the ability to liaise effectively across teams.