Financial Crime Data Scientist

Overview

The Financial Crime Data Scientist combines investigative expertise with advanced data science techniques to identify, assess, and mitigate financial risks, fraud, and emerging cyber-enabled threats. This role will analyze transactional, behavioral, and device-level signals; detect indicators of compromise; identify anomalous activity; and support intelligence integration into Appgate's Fraud security products. The analyst will collaborate closely with internal product teams and other external intelligence sources to track financial crime patterns (e.g., ransomware operators, malware families, account takeover trends, money mule networks) and translate insights into predictive models, detection rules, and automated workflows.

This candidate bridges fraud investigation, data analysis, and technical implementation while working cross-functionally with Product, Engineering, Risk, Marketing, and Operations. This is an on-site role with 3-5 days required in our NY office.

• Fraud & Threat Intelligence:
  Conduct in-depth investigations into financial crime activity, including transaction fraud, account compromise, synthetic identity, malware-enabled fraud, and ransomware monetization patterns
• Fraud & Threat Intelligence:
  Monitor intelligence feeds for emerging threat actors, TTPs, botnet activity, phishing kits, malware variants, and monetization schemes
• Fraud & Threat Intelligence:
  Identify fraud indicators, behavioral patterns, anomalies, and signal correlations across structured and unstructured data sources

• Data Analytics & Modeling:
  Collect, clean, engineer, and analyze large datasets using Python, SQL, and cloud-based data platforms
• Data Analytics & Modeling:
  Perform statistical analysis, clustering, anomaly detection, and supervised/unsupervised machine learning to improve predictive fraud scoring
• Data Analytics & Modeling:
  Build prototypes for fraud detection algorithms; partner with data science teams to product ionize models

• Data Engineering & Automation:
  Build and maintain analytical data pipelines with engineers using tools such as Airflow, dbt, Spark, or similar
• Data Engineering & Automation:
  Automate data ingestion (APIs, logs, intelligence feeds, enrichment sources) for ongoing fraud monitoring
• Data Engineering & Automation:
  Create dashboards and visualizations using Tableau, Power BI, Looker, Mode, or similar to communicate findings

• Cross-Functional Intelligence Integration:
  Translate fraud intelligence into actionable requirements for product and engineering teams (e.g., detection rules, model features, new risk signals)
• Cross-Functional Intelligence Integration:
  Collaborate with marketing and customer-facing teams to prepare intelligence briefs, threat summaries, and fraud trend reports
• Cross-Functional Intelligence Integration:
  Produce fraud loss metrics, risk scoring insights, and performance evaluations of prevention tools

• Security & Compliance:
  Maintain strict confidentiality and follow handling protocols for sensitive data, PII, and regulated financial information
• Security & Compliance:
  Stay current on fraud trends, sanctions, AML regulations, and industry standards

• Bachelors/Masters degree in Data Science, Applied Statistics, Digital Forensics, Financial Engineering, Criminology, Computer Science, Cybersecurity, or relevant field; or equivalent experience
• 1-3+ years in fraud detection, threat intelligence, financial crime investigations, cyber threat analysis, or risk operations
• Strong proficiency in:
  • SQL for data extraction and manipulation
  • Python (pandas, Num Py, scikit-learn) for data analysis
  • Data visualization tools (Tableau, Power BI, Looker, etc.)
• Familiarity with machine learning concepts, anomaly detection, statistics, and predictive modeling
• Experience with fraud platforms, case management systems, device intelligence, or behavioral analytics systems
• Demonstrated investigative mindset with excellent documentation and communication skills

• Experience with big data technologies (Spark, Databricks, Snowflake)
• Knowledge of fraud-specific data sources: device fingerprinting, behavioral biometrics,…