Senior Data Scientist – Payments Fraud

At Mamo, we’re redefining how businesses move and manage money with issuing and acquiring solutions — from corporate cards to a payment gateway and payment links — for fast-growing companies in the UAE and beyond. Our mission is to build the most secure, reliable, and intuitive payments platform, where trust and innovation go hand in hand.

We’re looking for an expert in payments fraud to shape the future of our fraud detection and prevention strategy, and strengthen our defenses.

Why you'll love working here

• Startup environment thats big on individual responsibility and leans on process and automation.
• Were big on culture. Work with stunning, supportive product, design and engineering teams on problems that matter.
• You will be learning and growing all of the time. From business, product, design to engineering you will be learning from a world-class team that is caring, kind, and empathetic.
• Mamo has the potential for a wide-reaching impact. Mamo is taking on the challenge of bringing about a new era of financial inclusion that begins close to home by providing access and experiences that make sense. That means you will never be bored.

What you will do

• Youll be a critical voice in ensuring that our systems are secure by design. 
• Youll work closely with cross-functional teams (Product, Engineering, Risk Operations, and Customer Experience) to build, refine, and scale robust fraud and security detection and prevention systems that protect our customers and our business.
• Lead design, implementation, and monitoring of fraud detection systems, dashboards, and analytics.
• Build scalable data pipelines for ingestion, transformation, feature engineering, and real-time scoring for fraud models.
• Analyze large datasets to uncover fraud patterns, emerging threats, and systemic weaknesses in existing rules or models.
• Develop, validate, and improve statistical & machine learning models that detect fraud and risky behavior.
• Proactively identify loopholes in our system to preempt and prevent potential exposure before it occurs.
• Holistically measure the financial impact of our fraud systems, to find the optimal balance of loss prevention from fraud vs. the opportunity cost of lost revenue from false positives.
• Work closely with Engineering to embed models into production workflows and ensure robust model monitoring, alerting, and performance feedback loops.
• Help define and refine internal processes for risk scoring, alert prioritization, and incident response.
• Own metrics and reporting tied to fraud outcomes — false positives/false negatives, loss rates, efficacy of interventions, and customer impact.

What we’re looking for

• 5+ years of experience in data engineering, data science, or analytics — ideally with a focus on payments fraud, financial crime, or risk detection.
• Strong SQL, Python (or equivalent), and experience with data engineering frameworks and cloud-native data platforms.
• Deep understanding of fraud detection techniques, statistical modelling, supervised/unsupervised learning, and anomaly detection.
• Hands-on experience building fraud rules, risk scores, transaction monitoring systems, and rule engines.
• Big-data experience and familiarity with real-time analytics, streaming data, or near-real-time scoring.
• Good communication skills and a collaborative mindset — you can explain complex technical work to non-technical stakeholders.
• A bias for action and the ability to independently prioritize ambiguous tasks in a fast-paced environment.
• Customer-centric mindset, where you understand the impact of every decision on our legitimate customers, and incorporate this into your work.

Bonus if you have

• Experience with payment ecosystem tooling (e.g., Sardine, Stripe Radar, Riskified, Sift, Forter, Fraud.net, Fingerprint).
• Familiarity with Visa/Mastercard payment fraud frameworks and standards.
• Background working in a licensed financial services or fintech environment.
• Advanced degrees in statistics, data science, engineering, or related quantitative fields.