Machine Learning Engineer - Fraud Risk

What you'll do

• Develop end-to-end ML pipelines and low-latency fraud decision systems, from data ingestion and feature engineering through deployment and monitoring.
• Own ML infrastructure, model versioning, retraining, deployment safety, and monitoring for performance, latency, data quality, and drift.
• Experiment with explainability, drift detection, and adversarial robustness, and partner with fraud risk, platform, data science, and compliance teams.

What they ask for

• 5+ years building production ML systems, including at least 2+ years in fraud, risk, or anomaly detection.
• Degree in Computer Science, Engineering, Statistics, Applied Math, or a related technical field.
• Advanced proficiency in Python and ML frameworks; proven track record designing and maintaining ML models at scale.
• Experience developing, validating, and productionalizing predictive real-time and offline fraud detection models using supervised and unsupervised ML techniques.

Nice to have

• Domain expertise in banking, payments, or transaction monitoring; experience with graph-based or network-level fraud detection.
• Experience adapting generative AI / large language models for pattern generation or synthetic data augmentation.

Pay

$170K – $240K USD base salary

Tools

Python, PyTorch, TensorFlow, scikit-learn

AI focus

Fraud detection, anomaly detection, and behavioral analysis using ML; nice-to-have work adapting generative AI / large language models for pattern generation or synthetic data augmentation.