• Analyze large, complex fraud datasets to identify patterns, trends, and anomalies that inform detection strategies and business decisions
• Evaluate existing static, rule-based fraud detection systems through data-driven assessments of their performance and coverage, and deliver clear, prioritized recommendations for rule updates, retirement, or new rule creation
• Partner with fraud operations teams to understand frontline detection challenges and translate operational insights into analytical hypotheses and actionable solutions
• Utilize AI-assisted development tools such as Amazon Q and Kiro to accelerate analytical workflows and solution delivery
• Prototype and contribute to the development of agentic AI applications leveraging AWS AgentCore and generative AI solutions that advance the team's fraud strategy capabilities
• Collaborate with fraud technology teams to ensure models, rules, and AI-driven outputs are implemented accurately and monitored effectively within the AWS production environment
• Design, build, and validate machine learning and statistical models to enhance fraud detection capabilities, improve precision and recall, and reduce false positive rates
• Monitor deployed models and fraud rules on an ongoing basis, identifying performance degradation or emerging detection gaps that require intervention
• Communicate findings, model results, and strategic recommendations clearly to both technical and non-technical stakeholders
• Stay current with emerging trends in fraud typologies, financial crime, and AI and machine learning developments within the AWS ecosystem, and bring relevant innovations back to the team
Requirements
- University (Degree) Preferred
- 5+ Years Required; 7+ Years Preferred
- 5+ years of hands-on experience in data science, analytics, or a closely related quantitative discipline
- Strong proficiency in Python or R for statistical analysis and model development
- Solid command of SQL and experience working with large-scale structured and unstructured datasets
- Demonstrated expertise in statistical modeling and machine learning techniques including classification, regression, clustering, and anomaly detection
- Ability to manage relationships across multiple stakeholder groups including operations and technology teams
- Proven ability to learn new domains, tools, and methodologies quickly and independently
- Solid understanding of model evaluation metrics for imbalanced classification problems (e.g., precision, recall, AUC, F1)
Core Competencies
Expertise in analyzing complex fraud datasets and developing machine learning models to enhance fraud detection capabilities. Proficient in utilizing AI-assisted tools and collaborating with cross-functional teams to implement effective fraud strategies.
Highest-signal resume keywords
- Python Proficiency
- SQL Expertise
- Statistical Modeling
- Machine Learning Techniques
- Data Analysis Experience
ATS Optimization Keywords
Hard Skills
- Data Science
- Statistical Analysis
- Model Development
- Anomaly Detection
- Classification Techniques
- Regression Techniques
- Clustering Techniques
- Model Evaluation Metrics
- Fraud Detection
- Data-Driven Assessments
Soft Skills
- Stakeholder Management
- Communication Skills
- Analytical Thinking
- Problem Solving
- Collaboration
Industry Keywords
- Fraud Detection
- Financial Crime
- Emerging Trends
- AI Developments
- Machine Learning
Tools & Technologies
- Amazon Q
- Kiro
- AWS AgentCore
- AI-Assisted Development Tools
- AWS Production Environment