About the Role
We are seeking an exceptional Principal Machine Learning Engineer to lead the design and development of the next generation of our AI-driven fraud detection platform.
You will architect large-scale ML systems that detect and prevent fraud in real time combining deep machine learning expertise with scalable engineering and domain knowledge in financial systems.
This is a hands-on technical leadership role, shaping our fraud prevention roadmap and ensuring the platform evolves to meet emerging threat patterns through automation, data intelligence, and generative AI-enhanced detection models.
Responsibilities
- 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 monitoring.
- Leverage modern AI techniques, including generative AI, to improve fraud pattern discovery and model robustness.
- Design and implement real-time decision systems, integrating with transaction or behavioral data streams.
- Collaborate closely with engineering, security, and risk teams to define data strategy and labeling frameworks.
- Lead experimentation on model explainability, drift detection, and adversarial robustness for fraud prevention use cases.
- Promote engineering excellence - automation, CI/CD, reproducibility, observability, and model governance.
- Mentor and guide ML and software engineers, fostering best practices and innovation.
Minimum Qualifications
- 5+ years of experience building ML or AI systems in production; at least 2+ in fraud, risk, or anomaly detection domains.
- Proven track record designing and maintaining ML pipelines at scale.
- Expertise in Python, ML frameworks (e.g., PyTorch, TensorFlow, scikit-learn), and CI/CD (GitHub Actions, Jenkins, or similar).
- Strong understanding of supervised / unsupervised learning, anomaly detection, and statistical modeling.
- Experience with big data and distributed systems (e.g., Spark, Kafka, Flink, or similar).
- Familiarity with cloud platforms (AWS, GCP, or Azure) and containerized deployments (Docker, Kubernetes).
- Strong collaboration, communication, and cross-team leadership skills.
Preferred Qualifications
- Prior experience with fraud or financial crime detection, identity verification, or risk scoring systems.
- Domain expertise in banking, payments, or transaction monitoring
- Experience fine-tuning or adapting generative AI / large language models for pattern generation or synthetic data augmentation.
- Familiarity with streaming analytics, graph ML, or time-series anomaly detection.
- Knowledge of model governance, bias mitigation, and regulatory compliance in fraud contexts.
- Contributions to fraud detection research, open-source, or AI publications.
What Success Looks Like
- Real-time AI-driven fraud prevention models with measurable reduction in false positives and detection latency.
- Scalable, automated ML pipelines enable faster experimentation and deployment.
- Cross-functional collaboration delivering tangible business impact in fraud loss reduction.
- A culture of ML excellence, experimentation, and continuous learning across the team.
Location: New York City
Department: AI / Fraud Prevention Engineering
Experience: 5+ years (Staff) or 8+ years (Principal) in ML or fraud detection systems
Compensation: 220-265k + bonus