Sr Data Scientist – Financial Crimes Detection

Job Summary

As a Data Scientist, you will apply your strategic and analytical skills to build monitoring solutions to combat money laundering. This job will lead development and implementation of advanced data science models and algorithms. You will work with stakeholders to understand requirements, analyze and derive insights from large volumes of data, implement monitoring solutions in a fast-paced environment while driving best practices in data science, ensuring data quality.

• Lead the development and implementation of advanced data science models.
• Collaborate with stakeholders to understand requirements.
• Drive best practices in data science.
• Ensure data quality and integrity in all processes.
• Mentor and guide junior data scientists.
• Stay updated with the latest trends in data science.

• Minimum of 5 years of relevant work experience and a Bachelor's degree or equivalent experience.

• Design and implement transaction monitoring rules and machine learning models to detect money laundering, structuring & fraud, across Pay Pal World's multi‑wallet payment rails.
• Develop and maintain feature engineering pipelines in Big Query, creating reusable primitives (velocity, growth ratios, concentration, dormancy signals) that serve multiple detection use cases.
• Partner with data engineering teams to define data requirements for new transaction types flowing through the network platform, ensuring detection‑relevant fields are captured from the start.
• Analyze transaction patterns across jurisdictions to identify emerging typologies unique to interoperable payment networks (e.g., cross‑wallet layering, dormant account exploitation via external funding, regulatory arbitrage across connected ecosystems).
• Build model validation frameworks including back testing against historical cross‑platform activity and false positive analysis to ensure detections are operationally sustainable.
• Translate detection outputs into actionable intelligence for compliance investigators, designing alert packages that provide sufficient context for efficient case resolution.
• Collaborate with compliance policy teams across multiple jurisdictions (FinCEN, AUSTRAC, CSSF, and others) to ensure detections satisfy local regulatory obligations as the platform expands.
• Produce clear documentation of detection methodology, threshold rationale, and model performance for regulatory examination and internal model governance review.
• Advise product and engineering teams on financial crime risk implications of new Pay Pal World features, payment flows, and partner integrations before they launch.

• 5+ years of experience building AML/fraud detection models or transaction monitoring systems at a financial institution, fintech, or payment network.
• Strong SQL skills with experience writing complex analytical queries against large‑scale transactional datasets (Big Query, Snowflake, or similar cloud data warehouses).
• Python proficiency for data analysis, feature engineering, and model development (pandas, scikit‑learn, or equivalent).
• Experience with Big Query ML, Tensor Flow, XGBoost, or similar frameworks for classification and anomaly detection.
• Understanding of AML regulatory frameworks (BSA/FinCEN, AUSTRAC, EU AMLD, FATF guidelines) and how detection systems map to regulatory obligations.
• Experience working with payment network data — understanding of P2P flows, funding instruments, settlement processes, and the distinction between sender‑side and receiver‑side risk signals.
• Comfort operating in ambiguity: ability to define your own work streams, make progress with incomplete data, and adapt as platform architecture evolves.
• Experience partnering with compliance investigators to understand how detections translate to actionable cases — you've seen the downstream impact of your models and tuned accordingly.
• Familiarity with graph‑based analysis or network detection methods for identifying linked accounts, collusion, or money movement networks.
• Strong communication skills — ability to explain model behavior to non‑technical compliance stakeholders…