Data Scientist

Company Description

Rasēd is a cutting-edge fraud detection and prevention solution designed for financial institutions, fintechs, and payment providers. It combines AI, device intelligence, and behavioral biometrics to detect and prevent fraud in real time while ensuring a seamless user experience. The platform also includes advanced analytics for post-incident investigation, compliance, and automated case management, enabling faster, smarter, and more secure fraud management.

Location: Riyadh, Saudi Arabia (Onsite)

Employment Type: Full-time

Role Purpose

We're looking for a Data Scientist to build and improve the models and rules that detect fraud, AML risk, and financial crime — from transaction monitoring to mule activity and account takeover. You'll own fraud analytics end to end, from data exploration to deployment and monitoring, working closely with fraud, compliance, and engineering teams.

Responsibilities

●    Contribute to the development and deployment of fraud detection, AML, and financial crime prevention solutions.

●    Build and improve models and rules that detect suspicious behavior, transaction fraud, mule activity, account takeover, sanctions risk, and abnormal customer patterns.

●    Translate fraud, compliance, and business requirements into practical analytical solutions, detection scenarios, dashboards, and workflows.

●    Own defined fraud analytics components end to end, from data exploration and feature engineering to testing, deployment, and monitoring.

●    Work with structured financial, customer, device, transaction, and case-management data to identify fraud patterns and risk indicators.

●    Conduct experimentation and optimization of fraud detection models, risk scoring logic, and scenario thresholds.

●    Support model deployment and monitoring in collaboration with engineering teams, ensuring fraud models remain accurate, explainable, and operationally useful.

●    Assist in tuning fraud scenarios, reducing false positives, improving detection rates, and measuring model effectiveness.

●    Interact with SME clients under guidance to understand fraud use cases, operational pain points, and regulatory expectations.

●    Stay updated with fraud trends, AML typologies, regulatory requirements, and industry best practices.

Qualifications

●    1–4 years of experience delivering data science, analytics, fraud detection, AML, or financial crime solutions.

●    Must have hands-on Python experience.

●    Must have experience or strong exposure to fraud detection, AML, risk analytics, transaction monitoring, or financial crime.

●    Strong proficiency in SQL and experience working with structured data.

●    Experience working with data such as transactions, customer profiles, device data, alerts, cases, or financial records.

●    Familiarity with feature engineering, data pipelines, model training, model evaluation, and deployment workflows.

●    Understanding of fraud detection concepts such as anomaly detection, risk scoring, false positives, behavioral patterns, mule accounts, and suspicious activity monitoring.

●    Strong analytical thinking and ability to connect data patterns to real-world fraud behavior.

●    Strong communication skills and ability to explain technical findings to business, fraud, and compliance teams.

●    Proficiency in English; Arabic is a plus.

Nice to have

●    Exposure to Generative AI, LLMs, prompt engineering, RAG, or AI-agent workflows.

●    Experience applying GenAI to fraud investigation, alert triage, sanctions screening, workflow automation, or case management.

●    Experience with model monitoring, MLOps, or production fraud systems.