Our Purpose
Mastercard powers economies and empowers people in 200+ countries and territories worldwide. Together with our customers, we’re helping build a sustainable economy where everyone can prosper. We support a wide range of digital payments choices, making transactions secure, simple, smart and accessible. Our technology and innovation, partnerships and networks combine to deliver a unique set of products and services that help people, businesses and governments realize their greatest potential.
Title and Summary
Lead Data Scientist (Graph Analytics)
Overview
Services within Mastercard is responsible for acquiring, engaging, and retaining customers by managing fraud and risk, enhancing cybersecurity, and improving the digital payments experience. We provide value-added services and leverage expertise, data-driven insights, and execution.
Role
We are seeking a highly skilled and motivated Lead Data Scientist to join our Cyber Analytics team within the Security Solutions Data Science organization. The successful candidate will play a leadership role in developing advanced analytics and machine learning solutions across cybersecurity, payments, and fraud. This person will also have formal people-management responsibilities for junior team members, helping them grow their technical capabilities, manage priorities, and deliver high-quality work.
Job Responsibilities
Lead the design, development, validation, and implementation of advanced analytical solutions, predictive models, and machine learning algorithms using large-scale payment, fraud, merchant, cybersecurity, and threat-intelligence data. Provide technical leadership for graph analytics and modeling, including graph schema design, relationship modeling, community detection, link analysis, graph embeddings, and graph neural networks – all in service of addressing real-world cybersecurity problems such as breaches, payment card testing, and scam rings. Develop models and analytical methods that identify complex or indirect risk patterns across interconnected entities such as payment cards, merchants, domains, service providers, fraud events, digital skimmers, technologies, vulnerabilities, and threat-intelligence indicators Apply graph algorithms and machine learning techniques to identify hidden communities, shared infrastructure, anomalous relationships, compromise paths, and patterns that cannot be sufficiently captured through transaction-level or entity-level models alone. Work hands-on with Python, SQL, Spark, Hadoop, and Databricks to develop scalable data-processing pipelines, reusable analytical datasets, model features, and production-ready solutions. Define appropriate performance metrics, validation strategies, monitoring requirements, and business-outcome measures for machine learning solutions. Translate ambiguous business, product, cybersecurity, and fraud problems into clearly defined analytical approaches, technical requirements, and delivery plans. Partner closely with product, data engineering, software engineering, cybersecurity, operations, and other data science teams to move analytical capabilities from research through production deployment. Communicate analytical findings, model performance, technical tradeoffs, risks, and business implications clearly to technical and non-technical stakeholders, including senior leadership. Provide regular coaching, technical guidance, career-development support, and actionable feedback to junior team members.
Show the full description
All About You
- Bachelor’s or Master’s degree in Data Science, Computer Science, Cybersecurity, Information Technology, Engineering, Mathematics, Statistics, Physics, or a related quantitative field.
- You are fundamentally a problem-solver who is comfortable entering complex and evolving problem spaces, identifying the most important questions, and developing practical analytical solutions.
- You have proven experience leading data science projects from problem definition and exploratory research through validation, implementation, and production handoff.
- You can translate complex technical results into clear business insights and communicate effectively and persuasively with both technical and non-technical audiences.
- You are a strong collaborator who can work across data science, product, engineering, cybersecurity, and operations teams.
- You are organized, accountable, and comfortable managing multiple priorities in an environment where analytical requirements and technical architecture continue to evolve.
- You are confident working independently while maintaining the humility to seek additional expertise, consider alternative approaches, and incorporate feedback.
Technical Skills
- The candidate must bring substantial hands-on knowledge of graph analytics. This includes designing graph data models, engineering node and edge features, and developing graph-based machine learning solutions at scale.
