About the role
Role will operate primarily in feature engineering support for the Fraud AI/ML modeling team, with a focus on feature development and graph-based data assets. Personnel will engineer, maintain, and optimize features within the AWS Feature Store using PySpark; create and enhance graph relationships, node structures, and embeddings within Neo4j; support data quality monitoring and feature governance; and partner with modelers to enable scalable, production-ready data assets for fraud detection and risk analytics.
This role requires individuals with strong communication, problem-solving, and independent thinking skills.
Preferred Platform Experience:
- Experience working on AWS (or similar platform such as Azure / GCP)
- Experience developing data pipelines using PySpark
- Experience working with Neo4j and graph data modeling concepts
- Familiarity with feature stores, embeddings, and entity resolution techniques
- Essential - Experience engineering and deploying production-grade data features or pipelines in an enterprise environment
- Essential - Experience with graph analytics, knowledge graphs, embeddings, or network-based modeling techniques
- Nice to Have - Experience with Fraud Analytics, Strategy, Modeling, or Financial Crimes use cases
Languages and Tools:
- Advanced (Essential) - Python
- Advanced (Essential) - PySpark
- Advanced (Preferred) - Neo4j (Cypher, graph modeling, embeddings)
- Intermediate (Essential) - GitHub / Bitbucket
- Intermediate (Preferred) - SQL
- Intermediate (Preferred) - AWS Feature Store, EMR, Glue, or related cloud data services