Fraud Modeling – Graph Analytics Engineer
Experience: 3–10 Years
Location: Bengaluru / Gurugram
Notice Period: Immediate to 60 Days
Job Summary
We are seeking an experienced Fraud Modeling Engineer with expertise in graph databases and graph-based fraud detection solutions. The ideal candidate will have hands-on experience with graph technologies, graph query languages, and Graph Neural Networks (GNNs) to build scalable fraud detection and risk analytics models.
Key Responsibilities
Design and develop graph-based fraud detection models using graph databases.
Build and optimize graph data models for fraud analytics and risk detection.
Develop and execute graph queries using Cypher and Gremlin.
Work with AWS Neptune and/or Neo4j for graph database implementation.
Build and deploy Graph Neural Network (GNN) models for fraud detection and link analysis.
Analyze complex relationships and patterns to identify fraudulent activities.
Collaborate with data scientists, engineers, and business stakeholders to deliver fraud analytics solutions.
Optimize graph database performance and ensure scalability of fraud detection systems.
Required Skills
Strong experience in Fraud Modeling and Fraud Analytics.
Hands-on experience with AWS Neptune and/or Neo4j.
Proficiency in Cypher Query Language and Gremlin.
Experience with Graph Neural Networks (GNNs).
Solid understanding of graph data structures, relationship modeling, and network analytics.
Good analytical and problem-solving skills.
Excellent communication and stakeholder management skills.
Preferred Skills
Experience in Financial Services, Banking, or FinTech fraud detection.
Knowledge of Machine Learning and AI techniques for fraud prevention.
Experience working with cloud platforms, preferably AWS.
Familiarity with Python or Java for graph analytics is an added advantage.
Mandatory Skills
Fraud Modeling
AWS Neptune
Neo4j
Cypher Query
Gremlin
Graph Neural Networks (GNN)