Contract Duration: 3 Months
Engagement: Senior-Level Consulting / Contract
Workstream: Module B – Graph Analytics & Machine Learning
About the Role
We are looking for an experienced Senior Graph Data Scientist / ML Lead to lead the machine learning and graph analytics workstream for a 3-month engagement.
The successful candidate will be responsible for designing and implementing graph-based features, enhancing existing machine learning models, and applying advanced analytics to support fraud detection and behavioural risk identification.
This is a hands-on technical leadership role requiring strong experience in graph analytics, Python-based machine learning pipelines, and fraud detection.
Key Responsibilities
- Lead the delivery of Module B – Graph Analytics & Machine Learning.
- Design and develop graph-based features and analytics for fraud detection.
- Build and maintain the graph feature engine.
- Work with graph technologies such as NetworkX, Neo4j, or equivalent platforms.
- Develop and enhance Python-based machine learning pipelines.
- Identify relationships, patterns, networks and behavioural signals within transactional data.
- Enhance existing fraud detection models using graph-derived features.
- Conduct model experimentation, validation and performance assessment.
- Collaborate closely with the Data Scientist and MLOps Engineer.
- Translate complex analytical findings into practical fraud detection solutions.
- Ensure solutions are scalable, reproducible and suitable for production deployment.
- Provide technical leadership and guidance across the graph analytics and ML workstream.
Required Experience & Skills
- Proven senior-level experience in Data Science, Machine Learning or Graph Data Science.
- Hands-on experience with graph analytics and graph data technologies.
- Strong Python development and machine learning pipeline experience.
- Experience with NetworkX, Neo4j or equivalent graph technologies.
- Proven experience in fraud detection, preferably within financial services or transactional environments.
- Strong understanding of feature engineering and model enhancement.
- Experience working with transactional and behavioural datasets.
- Strong knowledge of machine learning methodologies and model evaluation.
- Experience taking analytical solutions from development through to production.
- Strong problem-solving and analytical skills.
- Ability to lead technical delivery while remaining hands-on.
Advantageous
- Experience with real-time or near-real-time fraud detection.
- Experience with graph-based machine learning.
- Experience in banking, payments, financial services or other regulated environments.
- Knowledge of MLOps and production model deployment.
Engagement
This is a 3-month senior-level engagement requiring dedicated involvement across the full project lifecycle.
Ideal candidate: A hands-on technical leader who combines deep machine learning expertise with practical graph analytics and proven fraud detection experience.