Job Description
Key Responsibilities
Card Fraud Model Development \& Optimization: Design, develop, and optimize card fraud detection models for issuing and acquiring portfolios. Implement advanced statistical, machine learning, and AI techniques to improve fraud detection accuracy and precision and minimizing false positives.
Model Hosting \& Deployment: Deploy models using SAS SFD and integrate with production systems. Ensure seamless hosting and scalability of models across multiple environments.
MLOps \& Automation: Establish and maintain MLOps pipelines for continuous integration, deployment, and monitoring of fraud models. Automate model retraining and performance tracking processes.
Evaluation \& Testing: Conduct rigorous model validation, stress testing, and performance benchmarking. Collaborate with fraud operations teams to ensure models meet business and regulatory requirements.
Collaboration \& Stakeholder Management: Partner with fraud risk, data engineers, IT and business teams to deliver end-to-end solutions. Communicate insights and recommendations to senior management and business stakeholders.
Required Skills \& Qualifications Education: Master’s or Ph.D. in Data Science, Statistics, Computer Science, or related field.
Technical Skills: Strong proficiency in SAS (including SAS SFD), Python, and SQL.
Experience with machine learning frameworks (e.g., TensorFlow, PyTorch, Scikit-
learn). Hands-on experience with MLOps tools and practices (e.g., MLflow,Kubeflow, CI/CD pipelines). Deep understanding of card fraud detection techniques and transaction data.
Experience: 7+ years in data science roles, with at least 3 years in card fraud
modeling. Proven track record of deploying models in production environments.
Soft Skills: Strong analytical and problem-solving skills. Excellent communication
and stakeholder management abilities.
Preferred Qualifications Experience in banking or payments industry.
Familiarity with cloud platforms (AWS, Azure, GCP) for model hosting and
deployment.
Knowledge of regulatory compliance in fraud risk management.