Staff Data Scientist (Fraud & Risk)
Core
Building and scaling production-grade classical ML and GenAI models to detect, mitigate, and investigate global fraud for a fintech serving SMEs.
Role type
Staff Individual Contributor (IC) Data Scientist (Fraud & Risk)
Builds
Production fraud detection systems, GenAI/Agentic AI workflows for alert handling, and real-time/batch risk decisioning pipelines.
Domain
Fintech / Banking / Fraud Detection
Deliverable
production ML models
Required skills
Classical Machine Learning (XGBoost, LightGBM, Random Forests, SVMs), Imbalanced Data handling, Data Drift & Concept Drift detection, Python, SQL, Synthetic Data generation, GenAI & Agentic AI (LangGraph, AWS Bedrock, GCP), Feature Engineering, Big Data (Spark, Hadoop), Cloud (AWS, GCP)
Preferred skills
Research publications, Patents, Open-source contributions
Technologies
Databricks, Snowflake, BigQuery, Tecton, Fiddler, LangGraph, PyTorch, Hugging Face
Responsibilities
Design and develop advanced predictive ML models for fraud detection and risk assessment; Implement and scale production-ready GenAI and Agentic AI workflows; Resolve data drift and concept drift in production pipelines; Collaborate with ML engineers to deploy models and establish CI/CD pipelines; Partner with Data Engineering to optimize feature stores for real-time decisioning; Translate complex fraud typologies into mathematical formulations; Build and track metrics for model performance and business impact.
Seniority
Staff, hands-on IC with technical leadership
