Principal Data Scientist

• Define the technical roadmap and architecture for the full fraud suite: transaction fraud detection, 3DS friction reduction, enrolment fraud, merchant fraud, cardholder risk scoring, CSR-quality NLP scoring, the internal RAG chatbot, and the agentic digital-CSR system.
• Lead an organization of ~20, including senior data scientists - set standards, grow talent, align teams on priorities, and resolve both internal and external conflicts.
• Own the most complex client escalations: when banks report missed fraud or false declines, lead the root‑cause analysis, drive systemic pipeline improvements, and discover new features that raise precision and recall across the suite.
• Champion feature and model innovation - set the bar for hypothesis‑driven EDA, evaluate emerging techniques (deep learning, LLMs, RAG, agentic AI), and decide where to invest.
• Engage executives and clients directly - represent the data science function to senior management and banking partners, present results and strategy, and address concerns with credibility.
• Establish platform and MLOps standards for scale, reproducibility, monitoring, and reliability across all teams.
• De‑risk delivery: balance technical excellence with business outcomes, timelines, and regulatory/compliance expectations in a financial‑services context.

We are looking for

• Experience: 10+ years of data science / ML experience with a strong record of production models at scale.

Skills

• Deep expertise in Python and advanced SQL, plus strong command of ML/DL theory / MLand practice (imbalanced classification, calibration, interpretability).
• Demonstrated success architecting end‑to‑end ML systems and setting technical strategy.
• Proven ability to lead ~20 people, including senior Data Scientists, and to resolve internal and external conflicts.
• Excellent executive presence - able to influence management and clients and translate technical work into business value.
• Strong grasp of fraud/risk or payments problem domains.

Nice‑to‑have (bonus)

• Production experience with LLMs, RAG, and Agentic AI systems (e.g., internal knowledge chatbots, digital CSR agents).
• Hands‑on depth in deep learning, XGBoost, and NLP.
• Direct experience in issuer processing / card payments - authorizations, 3DS, enrolment, merchant risk, chargebacks.
• Track record of published work and thought leadership in fraud, risk, or applied ML.
• Experience with Data Engineeringand MLOps tools (like Docker/Kubernetes, Spark, Airflow), Git, and visualization tools (matplotlib/plotly).