Lead Data Scientist – Scams Prevention

Overview

In this Lead Data Scientist role within Wise’s Scam Prevention team, you will build and deploy advanced models to detect fraud, focusing on account takeover and scam threats. You’ll work with cross-functional partners to translate security needs into data solutions that safeguard users while preserving seamless service. Your work will shape Wise’s risk posture and fraud prevention capabilities at scale, including real-time detection and incident response. The role offers a meaningful impact on the security of a global payments platform and opportunities to mentor others.

Responsibilities

• Lead development and deployment of ML models to detect and mitigate account takeover and scam threats
• Analyze large datasets to identify trends and anomalies related to ATO and Send Scam
• Design experiments to evaluate fraud detection systems and improve performance
• Collaborate with security analysts and engineers to convert requirements into data insights and solutions
• Develop data pipelines, algorithms, and tools for real-time detection and response
• Stay updated on advances in data science and fraud prevention to maintain state-of-the-art capabilities
• Mentor and guide junior data scientists to foster collaboration and learning

Key requirements

• Proven experience in data science with fraud detection, cybersecurity, or fintech domains
• Experience building ML models for Send Scam (Victim Identification) and Account Takeover (ATO)
• Strong proficiency in Python, R, or similar languages
• Experience with large datasets and processing tech (Hadoop, Spark, SQL)
• Familiarity with anomaly detection, supervised/unsupervised learning, deep learning, graph-based solutions
• Ability to communicate complex concepts to non-technical stakeholders
• Proactive problem-solving mindset with focus on protecting users
• Knowledge of Python and capability to justify design decisions; experience with Git/GitHub and reviewing code; ability to read Java
• Experience mining event logs to identify patterns and associations
• Experience with diverse model types and choosing appropriate methods (gradient boosting, neural networks, regression, autoencoders, clustering)
• Strong statistical analysis and ability to present insights for action
• Product-minded, able to work independently in cross-functional settings
• Good communication skills for non-technical audiences
• Strong problem-solving skills to refine statements and solutions

• collaboration
• communication
• proactive problem-solving
• Python
• R
• Hadoop

…