Machine Learning Engineer, Fraud

• Strong proficiency in Python and machine learning libraries such as scikit-learn, PyTorch, LightGBM. • Experience with backend development for deploying ML models to production environments is required. • Knowledge of building intelligent user graphs to model behavioral patterns, collusion networks, and account connectivity. • Ability to develop scalable data pipelines and real-time inference systems that support high-volume, low-latency machine learning workloads. • Experience in conducting deep behavioral and adversarial data analysis for fraud detection is necessary. • Skills in partner cross-functionally with Trust & Safety, Payments, and Infrastructure teams to develop features, labels, and model evaluation pipelines are required. • Competence in implementing monitoring systems that ensure reliability and responsiveness of models used for detecting fraudulent behaviors is needed. • Experience leading the end-to-end architecture design, development, testing, deployment, maintenance, and scaling of fraud detection, prevention, and intervention systems while balancing platform security with a seamless user experience. • Ability to define and track key metrics and dashboards for evaluating the effectiveness of fraud detection methods such as precision, recall, false-positive rate, latency is required. • Experience in staying ahead of emerging fraud tactics and continuously translating insights into adaptive systems that can be rapidly deployed to production environments needed. • Bachelor’s degree in Computer Science or a related field with 2–6 years of experience in machine learning, risk assessment, trust & safety domains is required.