Job Description
Ready to take your career global?
Make your mark at one of the biggest names in payments. We are seeking a hands-on Lead Risk Data Scientist & ML Engineer to own the full lifecycle of fraud detection and risk models. This role combines deep data science expertise with practical AI/agentic workflow experience and the infrastructure knowledge needed to ship at scale.
What You’ll Own
In this role, you'll own the end-to-end delivery of detection models and AI-assisted workflows that power fraud, credit, and AML risk operations. You'll drive model performance through the full lifecycle, from design and validation through production deployment and continuous optimization. You'll translate regulatory requirements and operational needs into detection strategies and technical execution plans, partner across Risk, Compliance, and Technology to ensure alignment, and lead project teams through complex, ambiguous detection challenges. This is a hands-on role that combines deep technical leadership with pragmatic problem-solving in a small, high-impact team.
Model Development & Deployment (End-to-End)
- Own the full lifecycle of ML models: design, development, validation, deployment, and serving in production
- Lead model performance monitoring and continuous refinement using production data and investigation outcomes
- Ensure models are explainable, auditable, and aligned with regulatory expectations
- Design and oversee scalable batch and real-time data pipelines supporting model development and serving
AI & Agentic Workflows
- Design and deploy AI-assisted analyst workflows using LLMs and agentic frameworks
- Guide the development of agent-based systems that augment human decision-making in risk operations
- Work at the pilot/proof-of-concept stage, establishing best practices for scale
Detection Strategy & Performance
- Define and refine detection strategies based on emerging fraud patterns and regulatory requirements
- Maintain and monitor key performance metrics (precision, recall, false positives, alert quality)
- Influence tradeoff decisions between detection coverage, operational cost, and false positive rates
Governance & Regulatory Alignment
- Define governance standards for model development, validation, documentation, and change management
- Ensure compliance with regulatory expectations (BSA/AML, OFAC, FinCEN, SR 11-7)
- Partner with Model Risk Management and Compliance to support validation and regulatory reviews
Cross-Functional Partnership
- Serve as the primary technical partner to Fraud Operations, Compliance, and Technology teams
- Translate regulatory and operational requirements into technical execution plans
- Drive alignment across teams to enable effective detection capability implementation