About the roleAs a Lead Data Scientist for our Fraud team, you will be on the front lines of protecting our company and our customers. You will leverage your expertise in machine learning, statistics, and data analysis to design, build, and deploy sophisticated models that detect and prevent fraudulent activity in real-time. This is a high-impact role where you will see your work directly translate into protecting millions of dollars and ensuring a trustworthy platform for our users.
Responsibilities- Technical Leadership & Strategy: Define the long-term machine learning strategy for the fraud team, establish technical best practices, and mentor junior data scientists.
- End-to-End Model Development: Own the entire lifecycle of fraud detection models, from data exploration and feature engineering to model training, validation, deployment, and monitoring.
- Credit & Lending Fraud Mitigation: Design and develop models specifically targeted at lending fraud typologies, including synthetic identity fraud, first-party loan default fraud, and application fraud.
- Advanced Analysis: Conduct deep-dive investigations into emerging fraud patterns and user behavior, using clustering, outlier detection, network analysis, and other unsupervised techniques to uncover hidden risks and organized fraud rings.
- Experimentation: Design and execute A/B tests to measure the impact of new models, rules, and strategies on both fraud detection rates and user experience.
- Stakeholder Collaboration: Partner closely with Product, Engineering, Risk, and Operations teams to translate business needs into data science solutions, seamlessly integrate ML scores with rule engines, and communicate complex results to non-technical audiences.
- Productionalize Models: Deploy, monitor, and maintain machine learning models in a cloud environment, ensuring high availability and performance.
- Reporting & Visualization: Build and maintain dashboards using tools like Tableau or Looker to track key performance indicators (KPIs) like fraud loss rates, false positive rates, and model performance.
Requirements- Experience: 5+ years of experience in a hands-on data science role, building and deploying machine learning models.
- Leadership: Proven experience leading complex data science projects from inception to production, including setting technical direction and guiding peers.
- Python: Expert-level Python for data analysis and modeling (pandas, scikit-learn, etc.).
- SQL: Advanced SQL skills for complex data extraction and manipulation.
- Machine Learning Modeling: Deep experience with tree-based ML models (XGBoost, CatBoost, LightGBM) and statistical models (Logistic Regression, Lasso/Ridge).
- Model Explainability & Ethics: Deep understanding of model explainability frameworks (SHAP, LIME) and algorithmic fairness to ensure models comply with credit lending regulations.
- Sampling Techniques: Strong understanding of sampling techniques for handling highly imbalanced datasets.
- Unsupervised Learning: Practical experience with clustering and outlier detection techniques (e.g., K-Means, K Nearest Neighbors, Isolation Forest).
- Model Lifecycle & Cloud: Proven experience with the full modeling lifecycle, including model deployment, monitoring, and maintenance on a cloud platform like GCP, AWS, or Azure.
- Analytical Rigor: A solid foundation in statistics and experience designing and analyzing A/B tests.
- Communication: Excellent stakeholder management and communication skills, with a demonstrated ability to explain complex technical concepts to diverse audiences. Advanced English level.
Nice to have- Domain Experience: Direct experience in a FinTech, payments, or risk/fraud-focused role, particularly with exposure to credit or consumer lending.
- Alternative & Bureau Data: Experience working with traditional credit bureau data (Experian, Equifax, TransUnion) and alternative credit/identity data sources.
- Graph ML: Experience with Graph Neural Networks (GNNs) or graph analytics tools (e.g., Neo4j, NetworkX) to map complex fraud networks.
- Regulatory Familiarity: Familiarity with consumer lending regulations (e.g., FCRA, ECOA) and their impact on machine learning model development.
- MLOps: Hands-on MLOps experience (e.g., CI/CD for models, versioning, automated retraining).
- GCP / Vertex AI: Experience with Google Cloud Platform (GCP), especially Vertex AI.
- Spanish and/or Portuguese speaker
These are the applicable requisites, although equivalent competencies in any of the above will also be considered.
What We Offer- Base
- SF/NYC: $168,000 - $214,000
- Miami: $137,000 - $177,000
- Initial stock options grant
- Annual performance bonus
- Health, dental, and vision plans
- Continuous learning opportunities
- 401(k) with an employer's match
- Unlimited PTO
- Paid parental leave
- Empowering opportunities for growth in a dynamic entrepreneurial environment
