Asset & Wealth Management - Engineering - Fraud Detection & AI​/ML Strategy - Vice President - R

Role Purpose

The VP of Fraud Detection Engineering will lead the strategic development and implementation of advanced AI and Machine Learning models to safeguard the Consumer Deposit business. This leader is responsible for architecting a real-time fraud detection ecosystem that leverages multi-dimensional signals to identify and mitigate fraud vectors across the entire customer lifecycle. From initial acquisition and account opening to complex money movement and ongoing account management, the VP will be the primary technical authority for defending against synthetic fraud, third‑party account takeovers (ATO), and sophisticated financial crimes.

• 1. AI/ML Model Strategy & Implementation
  • Lead the design, training, and deployment of ML models (e.g., Gradient Boosted Trees, Transformers, Graph Neural Networks) to detect anomalies in real-time.
  • Develop frameworks to ingest and synthesize multiple fraud signals, including behavioral biometrics, device fingerprinting, geolocation, and cross‑platform transactional data.
  • Architect low‑latency inference pipelines that provide immediate "go/no‑go" decisions for high‑risk events like account applications and large‑value transfers.
• 2. Lifecycle Fraud Prevention
  • Implement robust models to identify synthetic identities and fraudulent applications during the customer acquisition phase.
  • Define technical standards for monitoring ACH, wire, and P2P transfers to detect unauthorized activity and "mule" account patterns.
  • Develop sophisticated behavioral baselines to identify third‑party account takeovers and session hijacking attempts.
• 3. Engineering Excellence & Scalability
  • Oversee the engineering of high‑throughput data pipelines capable of processing millions of daily events with sub‑second latency.
  • Lead the development of a centralized feature store to ensure consistency between model training and real‑time production environments.
  • Establish rigorous back‑testing, A/B testing, and monitoring frameworks to track model drift and ensure high precision/recall ratios.
• 4. Strategic Leadership & Collaboration
  • Stay ahead of emerging fraud trends (e.g., GenAI‑enabled deepfakes, automated bot attacks) by fostering a culture of continuous research and rapid prototyping.
  • Partner with the Chief Risk Officer (CRO), Product Leads, and Legal/Compliance teams to align technical fraud roadmaps with business growth and regulatory requirements.
  • Build and lead a world‑class team of ML engineers, data scientists, and backend engineers specializing in financial security.

• 8+ years of experience in software engineering or data science, with at least 6 years in a senior leadership role within Fraud or Risk Tech.
• Deep expertise in supervised and unsupervised learning, specifically for anomaly detection and classification in imbalanced datasets.
• Proficiency in Python, PySpark, and modern ML frameworks; experience with cloud‑native AI services (AWS Sage Maker, GCP Vertex AI).
• Strong understanding of banking protocols (ACH, ISO 20022) and identity verification standards (KYC/AML).

• Proven track record of reducing fraud loss rates while maintaining a seamless, low‑friction customer experience.
• Ability to translate complex model performance metrics into clear business impact for executive leadership.
• Deep understanding of the trade‑offs between false positives (customer friction) and false negatives (fraud loss).

• Master's in Computer Science, Statistics, Mathematics, or a related quantitative field.

Goldman Sachs is an equal opportunity employer and does not discriminate on the basis of race, color, religion, sex, national origin, age, veterans status, disability, or any other characteristic protected by applicable law.