About the Role
The role involves designing and implementing machine learning models to detect fraudulent activity and improve decision-making across payment and identity platforms.
Responsibilities
- Develop machine learning models to identify suspicious transaction behaviors
- Analyze large-scale user and transaction datasets for risk signals
- Collaborate with engineering teams to deploy models into production environments
- Evaluate model performance using statistical and A/B testing methods
- Create data visualizations to communicate findings to non-technical stakeholders
- Monitor model drift and implement retraining pipelines
- Contribute to data pipeline architecture improvements
- Work with cross-functional teams to define risk rules and thresholds
- Investigate emerging fraud patterns using exploratory data analysis
- Document modeling approaches and decision logic for compliance purposes
- Optimize feature engineering processes for real-time scoring systems
- Support the integration of third-party data sources into analytical workflows
- Participate in peer reviews of code and model design
- Translate business requirements into technical data solutions
- Maintain data quality standards across analytical systems
- Design experiments to validate risk mitigation strategies
- Use statistical methods to assess the impact of policy changes
- Ensure models comply with regulatory and fairness guidelines
- Develop anomaly detection systems for new account creation flows
- Assist in scaling data infrastructure for global transaction volume
Nice to Have
- Master’s degree in a quantitative discipline
- Experience in fintech or payments industry
- Background in cybersecurity or identity verification
- Publications or contributions in machine learning or data science
- Experience with deep learning frameworks
- Knowledge of graph-based fraud detection methods
- Familiarity with MLOps practices
- Experience working with large-scale streaming data
- Prior work on identity resolution systems
- Contributions to open-source data projects
Compensation
Competitive salary with performance-based incentives
Work Arrangement
Hybrid work model with office and remote flexibility
Team
Collaborative data science and engineering team focused on real-time decision systems
Our Mission
Building trust in digital economies by detecting fraud and verifying legitimate users in real time
Tech Stack
Python, PySpark, TensorFlow, Airflow, BigQuery, Kubernetes, Snowflake
Impact
Models developed directly influence approval rates, fraud loss reduction, and customer experience
Growth Opportunities
Opportunities to lead modeling initiatives and mentor junior team members
Interview Process
Initial screening, technical assessment, modeling case study, team interviews, final review
Available for qualified candidates
