Mamo
Senior Data Scientist – Payments Fraud
- Permanent
- Dubai, United Arab Emirates
- Experience 5 - 10 yrs
Job expiry date: 09/04/2026
Job overview
Date posted
23/02/2026
Location
Dubai, United Arab Emirates
Salary
Undisclosed
Compensation
Comprehensive package
Experience
5 - 10 yrs
Seniority
Senior & Lead
Qualification
Bachelors degree
Expiration date
09/04/2026
Job description
The Senior Data Scientist – Payments Fraud is a mission-critical role responsible for shaping and advancing fraud detection and prevention strategies within a fast-growing fintech payments environment. This position focuses on building secure, scalable, and data-driven systems that protect customers and the business from fraudulent activities across issuing, acquiring, payment gateway, and digital transaction solutions. The role requires deep expertise in payments fraud, statistical modeling, and machine learning, with the ability to design and implement real-time fraud detection systems that balance risk mitigation with customer experience. Working closely with Product, Engineering, Risk Operations, and Customer Experience teams, the Senior Data Scientist leads the development of fraud models, rule engines, risk scoring frameworks, and monitoring dashboards. The role includes building scalable data pipelines, identifying emerging fraud patterns, proactively detecting systemic weaknesses, and optimizing the trade-off between fraud losses and false positives. This position demands strong technical depth in SQL, Python, and cloud-native data architectures, combined with the ability to translate complex analytical findings into actionable business decisions. The ideal candidate thrives in high-growth startup environments, demonstrates ownership and independent thinking, and is motivated by building secure-by-design financial infrastructure that drives trust and innovation in the payments ecosystem.
Required skills
Key responsibilities
- Lead the design, implementation, and continuous improvement of fraud detection and prevention systems across payment products.
- Develop scalable data pipelines for ingestion, transformation, feature engineering, and real-time transaction scoring.
- Build, validate, and optimize statistical and machine learning models to detect fraudulent behavior and financial crime risks.
- Design and maintain fraud dashboards, performance tracking systems, and key risk indicators to monitor fraud trends and system effectiveness.
- Analyze large and complex datasets to uncover fraud patterns, emerging threats, and vulnerabilities within existing systems.
- Develop and refine fraud rules, transaction monitoring logic, and risk scoring methodologies.
- Proactively identify system loopholes and structural weaknesses to prevent potential fraud exposure before incidents occur.
- Measure and optimize the financial impact of fraud controls by balancing loss prevention against customer friction and false positive rates.
- Collaborate with Engineering teams to deploy models into production workflows, ensuring scalability, reliability, and monitoring capabilities.
- Establish model monitoring frameworks, alerting mechanisms, and feedback loops for continuous performance improvement.
- Define and enhance internal processes for alert prioritization, incident response, and risk operations efficiency.
- Own fraud-related performance metrics including false positives, false negatives, fraud loss rates, intervention efficacy, and customer impact.
- Provide clear and structured communication of analytical insights to both technical and non-technical stakeholders.
- Contribute to the evolution of the company’s fraud strategy by evaluating new technologies, tools, and methodologies.
Experience & skills
- Minimum of 5 years’ experience in data science, analytics, or data engineering roles with a strong focus on payments fraud, financial crime, or risk detection.
- Advanced proficiency in SQL and Python (or equivalent programming language) for data manipulation, modeling, and analysis.
- Deep understanding of fraud detection methodologies including supervised and unsupervised learning, anomaly detection, and behavioral analytics.
- Hands-on experience building fraud rule engines, risk scoring systems, and transaction monitoring frameworks.
- Experience working with large-scale datasets, real-time analytics systems, streaming data, or near-real-time scoring architectures.
- Strong experience deploying machine learning models into production and maintaining performance monitoring systems.
- Excellent communication skills with the ability to explain complex technical findings to cross-functional stakeholders.
- Ability to operate independently in a fast-paced, high-growth environment with ambiguous priorities.
- Strong analytical mindset with structured problem-solving capabilities and high attention to detail.
- Customer-centric thinking with awareness of the balance between fraud prevention and customer experience.
- Experience working within licensed financial services or fintech environments is preferred.
- Familiarity with payment fraud tools and platforms such as Stripe Radar, Riskified, Sift, Forter, or similar solutions is advantageous.
- Knowledge of Visa and Mastercard fraud frameworks and payment network standards is a plus.
- Advanced degree in statistics, data science, engineering, or a related quantitative discipline preferred.