Advance your career as a Staff Engineer focusing on Data Science within our payments platform. This role is pivotal in designing, building, and deploying sophisticated machine learning models.

You will tackle critical use cases including real-time fraud detection, authorization optimization, risk scoring, and anomaly detection in transactional data. Operating in a regulated, low-latency environment, your work will prioritize model accuracy, explainability, and robust performance.

This position uniquely blends data science expertise with payments domain knowledge and production ML engineering skills. You'll collaborate closely with Fraud & Risk, Engineering, Compliance, and Product teams to ensure your data-driven models are effectively deployed and operational, not just theoretical.

Develop and deploy machine learning models for diverse applications such as real-time fraud detection, CNP risk scoring, authorization optimization, and anomaly detection in payment data.

Engineer advanced features from transactional and behavioral data, ensuring adherence to strict latency requirements for real-time scoring.

Select and implement appropriate ML techniques, including gradient boosting, deep learning, and anomaly detection, based on specific problem requirements.

Collaborate with engineering teams to integrate models into production pipelines, emphasizing reliability, monitoring, and safety.

Establish and maintain comprehensive model monitoring systems to track drift, data quality, and performance degradation, linking them to key business metrics.

Contribute to and champion MLOps best practices, including versioning, reproducible pipelines, CI/CD for models, and A/B testing frameworks.

Leverage modern AI and LLMs, such as Claude, to enhance data science workflows, automate feature exploration, and generate model documentation.

Explore the application of LLMs for generating risk and compliance narratives, aiding in tasks like Suspicious Activity Report drafting.

Partner with Fraud & Risk and Compliance teams to ensure model outputs are explainable and defensible to auditors and regulators.

Present complex model performance and findings clearly to non-technical stakeholders, facilitating informed business decisions.

Ensure strict adherence to data handling regulations, including PCI DSS and data residency requirements, particularly concerning sensitive cardholder data.

Possess over 10 years of professional experience, with a minimum of 3 years dedicated to Data Science or ML Engineering roles. Prior experience in payments, fintech, banking, or high-volume transactional data environments is highly desirable.

Demonstrate strong proficiency in Python (including libraries like pandas, scikit-learn, XGBoost/LightGBM, PyTorch or TensorFlow) and SQL for data analysis and model development.

Showcase proven experience in building and deploying machine learning models into production environments, with a keen focus on monitoring and retraining strategies.

Exhibit a solid understanding of classification, anomaly detection, and handling imbalanced datasets, crucial for tackling rare-event problems like fraud.

Have practical experience with cloud-based data and ML infrastructure (e.g., AWS SageMaker, GCP Vertex AI, Azure ML) and standard data engineering tools such as Spark and Airflow.

Possess a clear understanding of the regulatory landscape and security considerations for financial services data, including PCI DSS and data minimization principles.

Exhibit excellent communication skills, enabling you to translate technical model insights and trade-offs into actionable business decisions for risk and product teams.