Machine Learning Engineer - Fraud Risk

About the Team

The fraud risk management team at Rain creates sophisticated, scalable risk mitigation solutions to protect our customers and deliver a low-friction experience. We achieve this by maintaining transaction and lifecycle event monitoring, building alerts to speed fraud detection and response, and creating risk rules and strategies powered by ML models. We are a pillar of the business, supporting new products and ensuring their success. Rain’s next-generation payment technology introduces new fraud vectors that require holistic, end-to-end thinking, strong data fundamentals, and fraud management savvy to combat.

What you’ll do

• Architect and build scalable ML systems for fraud detection, anomaly detection, and behavioral analysis

• Develop and maintain end-to-end ML pipelines: data ingestion, feature engineering, model training, deployment, and continuous monitoring

• Design and implement low-latency, real-time decision systems partnering with fraud risk data scientists, integrating with transaction or behavioral data streams

• Own ML infrastructure, including model versioning, automated retraining, and safe deployment strategies (e.g., shadow, rollback)

• Build robust monitoring and alerting for model performance, latency, data quality, and drift

• Lead experimentation on model explainability, drift detection, and adversarial robustness for fraud prevention use cases

• Develop tooling and processes to improve the effectiveness and speed of the ML development lifecycle

• Partner with platform teams to meet strict SLAs for availability, latency, and accuracy

• Collaborate closely with talented engineers, data scientist and compliance teams across Rain

• Work in a fast-paced environment on a rapidly growing product suite

• Solve complex problems at the intersection of ML systems, data, and reliability

What we're looking for

• 5+ years of experience building ML systems in production; at least 2+ in fraud, risk, or anomaly detection domains

• A degree in Computer Science, Engineering, Statistics, Applied Math, or a related technical field

• Proven track record designing and maintaining ML models at scale

• Advanced proficiency in Python and ML frameworks (e.g., PyTorch, TensorFlow, scikit-learn)

• Strong understanding of supervised/unsupervised learning, anomaly detection, and statistical modeling

• Ability to work autonomously, manage ambiguity, and collaborate closely with data scientists to translate analytical models into robust fraud prevention systems

• Experience developing, validating, and productionalizing predictive real-time and offline fraud detection models using supervised and unsupervised ML techniques

• Experience collaborating with cross-functional teams to prioritize, scope, and deploy MLI solutions at scale

Nice to have, but not mandatory

• Domain expertise in banking, payments, or transaction monitoring

• Experience with graph-based or network-level fraud detection techniques

• A graduate degree in Computer Science, Engineering, Statistics, Applied Math, or a related technical field

• Experience fine-tuning or adapting generative AI / large language models for pattern generation or synthetic data augmentation (in partnership with data science)

• Knowledge of model governance, bias mitigation, and regulatory compliance in fraud contexts

Things that enable a fulfilling, healthy, and happy experience at Rain: