Applied AI & ML Lead [Multiple Positions Available]

DESCRIPTION:

Duties: Design and develop advanced machine learning (ML) models to detect fraudulent merchant activity and assess payer risk.

Engineer graph-based features and embeddings by constructing transaction-level payment graphs across cross-functional teams and applying Graph Neural Networks (GNN) to generate features for fraud detection models.

Extract and compute graph connectivity metrics such as PageRank, centrality scores, community detection and label propagation algorithms to identify fraudulent clusters and potential fraud rings within the merchant network.

Track and report rule-level model performance metrics, ensuring model interpretability and compliance.

Lead model development lifecycle, cross-functional initiatives, and research efforts focused on AI and ML innovation in the trust and safety domain, driving the adoption of scalable, explainable, and high-performing solutions for merchant fraud detection in financial services.

Analyze data trends and model outputs to identify potential areas for enhancement and to drive strategic adjustments within the division.

Collaborate with machine learning serving teams to deploy production-grade models at real-time pay-in and pay-out transaction checkpoints, ensuring low-latency fraud detection and integration with business-critical systems.

QUALIFICATIONS:

Minimum education and experience required: Master's degree in Computer Science, Information Technology or related field plus 2 years of experience in the job offered or as Applied Al & ML Lead, Applied Al & ML Scientist/Researcher, Software Engineer, or related occupation.

The employer will alternatively accept a Bachelor's degree in Computer Science, Information Technology or related field plus 5 years of experience in the job offered or as Applied Al & ML Lead, Applied Al & ML Scientist/Researcher, Software Engineer, or related occupation.

Skills Required: This position requires two (2) years of experience with the following: developing and deploying end-to-end supervised and unsupervised ML models, including Decision Trees, XGBoost, LightGBM, and K- means, for fraud detection in the financial services or payments industry; working with high throughput real-time transactional data at scale; using Docker, Kubernetes, and CI/CD pipelines to deploy models such as gradient boosted trees or deep learning architectures; developing graph- based ML solutions for fraud detection with GNNs using GraphSAGE, node2vec, metapath2vec, or Graph Attention Networks; leveraging Pytorch Geometric or NetworkX; creating risk scores using temporal features, rolling aggregates, and longitudinal modeling to support fraud prevention KPIs; building distributed data pipelines for feature engineering and model training using PySpark, Apache Beam, Kafka, and Airflow; building data warehouses that focus on feature freshness and low latency using stacks that leverage BigQuery or Snowflake; using Python, TensorFlow, PyTorch, Scikit-learn, Keras, XGBoost, and ...