Data Scientist

About Rasēd

Rasēd is an advanced fraud detection and prevention platform tailored for financial institutions, fintech companies, and payment providers. It integrates artificial intelligence, device intelligence, and behavioral biometrics to detect fraud in real-time while maintaining a smooth user experience. The solution includes sophisticated analytics for post-event investigations, regulatory compliance, and automated case management, enabling rapid, intelligent, and secure fraud handling.

Position Overview

We are seeking a Data Scientist to enhance and develop models and rules aimed at identifying fraud, anti-money laundering (AML) risks, and other financial crimes—covering areas such as transaction monitoring, mule account activity, and account takeovers. The role involves end-to-end ownership of fraud analytics from initial data analysis through deployment and ongoing monitoring, collaborating closely with fraud, compliance, and engineering teams.

Key Responsibilities

• Assist in building and implementing fraud detection, AML, and financial crime prevention solutions.
• Develop and refine models and rule sets that detect suspicious conduct, transactional fraud, mule activities, account takeovers, sanctions risks, and unusual customer behaviors.
• Transform fraud, compliance, and business needs into practical analytical methods, detection frameworks, dashboards, and workflow processes.
• Manage specific fraud analytics components comprehensively—from data exploration and feature development to testing, deployment, and monitoring.
• Analyze structured datasets including financial transactions, customer information, device data, and case management records to identify fraudulent patterns and risk markers.
• Conduct experiments and optimize detection models, risk scoring mechanisms, and scenario thresholds.
• Support model deployment and monitoring alongside engineering teams to ensure models maintain accuracy, transparency, and operational effectiveness.
• Help adjust fraud detection scenarios to reduce false positives, increase detection rates, and assess model performance.
• Collaborate under guidance with subject matter experts and clients to grasp fraud-related use cases, operational challenges, and regulatory needs.
• Keep abreast of emerging fraud trends, AML typologies, regulatory developments, and sector best practices.

Required Qualifications

• Between 1 to 4 years of practical experience in data science, analytics, fraud detection, AML, or financial crime solution domains.
• Proficient in Python programming.
• Demonstrated experience or solid exposure to fraud detection, AML, risk analytics, transaction monitoring, or related financial crime areas.
• Strong SQL skills and experience working with well-structured data.
• Experience handling data types such as transactions, customer profiles, device data, alerts, cases, or financial documents.
• Understanding of feature engineering, data pipeline construction, model training and evaluation, and deployment workflows.
• Familiar with fraud detection principles like anomaly detection, risk scoring, false positive management, behavioral analysis, mule accounts, and suspicious activity tracking.
• Excellent analytical abilities to relate data patterns to actual fraud behaviors.
• Effective communication skills to convey technical results to teams across business, fraud, and compliance functions.
• Proficiency in English; knowledge of Arabic is advantageous.

Desirable Skills

• Experience with Generative AI, large language models, prompt engineering, retrieval-augmented generation, or AI-driven agent workflows.
• Applied experience of GenAI solutions in fraud investigation, alert prioritization, sanctions screening, workflow automation, or case management.
• Knowledge of model monitoring, ML operations (MLOps), or production-scale fraud detection systems.

Location and Employment Details

This is a full-time position based onsite in Riyadh, Saudi Arabia.