Lead Data Scientist, Spend

About Wise

Wise is a global technology company, building the best way to move and manage the world’s money. We offer minimal fees, maximum ease, and full speed for sending money to another country, spending abroad, or making and receiving international payments. Our mission is to make lives easier and save customers money. As part of our team, you will contribute to creating an entirely new global network for money, for everyone, everywhere.

Role Overview

As a Lead Data Scientist on the Spend team, you will use your data science expertise to innovate and deploy models that enhance our card fraud detection capabilities and optimize card product performance. Your work will directly impact our ability to protect customers during card transactions while also driving card adoption and retention. You will collaborate closely with cross-functional teams, including engineering, product, and risk management.

What You'll Be Doing

• Lead the development and deployment of advanced machine learning models to improve card fraud detection and optimize card product performance across various Wise markets.
• Analyze extensive transaction data to identify trends, patterns, and anomalies related to fraudulent card activity and customer behavior.
• Design and implement experiments to evaluate the effectiveness of fraud detection systems and card product features, driving continuous performance improvement.
• Design and deploy LLM-based risk handling automation components to enhance decision-making and streamline risk response workflows.
• Collaborate with analysts, risk teams, and engineers to translate business requirements into actionable data insights and solutions for card issuance, fraud prevention, and retention.
• Develop robust data pipelines, algorithms, and tools to support real-time fraud detection and card product optimization.
• Stay informed about the latest advancements in data science, machine learning, and payment fraud prevention techniques to maintain state-of-the-art capabilities in the Spend domain.
• Mentor and guide junior data scientists, fostering a culture of collaboration and continuous learning within the team.

What You'll Need

• Proven experience in a data science role, with a bonus for experience in the card domain, fraud detection, anti-money laundering, or fintech.
• Strong proficiency in machine learning frameworks and programming languages such as Python, R, or similar.
• Experience working with large datasets and data processing technologies (e.g., Hadoop, Spark, SQL).
• Experience designing and deploying LLM-based solutions in production.
• Familiarity with anomaly detection, supervised and unsupervised learning methods, and real-time data analysis.
• Demonstrated ability to work collaboratively in cross-functional teams and effectively communicate complex technical concepts to non-technical stakeholders.
• A proactive, problem-solving mindset with a passion for protecting users from criminal activities.
• Solid knowledge of Python, with the ability to make and justify design decisions in your code.
• Proficiency in using Git for collaboration (e.g., opening Pull Requests on GitHub) and code review.
• Ability to read through code, especially Java.
• Demonstrable experience collaborating with engineering on services.
• Experience working with compliance to assure the effectiveness of controls.
• Familiarity with a range of model types, understanding when and why to use gradient boosting, neural networks, regression, autoencoders, clustering, or a blend.
• Experience with statistical analysis and good presentation skills to translate insight into action.
• A strong product mindset with the ability to work independently in a cross-functional and cross-team environment.
• Good communication skills and the ability to convey points to non-technical individuals.
• Strong problem-solving skills with the ability to help refine problem statements and devise solutions.

Key skills/competency

• Machine Learning
• Fraud Detection
• Python
• SQL
• LLM Deployment
• Data Analysis
• Risk Management
• Cross-functional Collaboration
• Anomaly Detection
• Data Pipelines