Fraud & FinCrime Data Analyst (Fintech)

Location: Belgrade, Europe; hybrid

Company

hirify.global is a global fintech building products and services for international money movement.

What you will do

• Own and improve the fraud and AML/TF rules lifecycle from hypothesis and backtesting through deployment, tuning, performance review, and retirement.
• Build KPI frameworks and activity tracking for detection effectiveness, false positives, losses, alert volumes, rule changes, and operational productivity.
• Analyze real-time and batch transaction data, identify anomalies and emerging attack patterns, and investigate loss drivers and rule performance.
• Replace manual analysis and reporting with scalable pipelines, scheduled jobs, and self-service dashboards.
• Partner with Product, Engineering, Compliance, Network, and Operations on detection requirements, audits, Visa and Mastercard monitoring, and investigation feedback.
• Document rule decisions, support AML regulations, PSD2/SCA, and card-scheme controls, and escalate material risks.

Requirements

• Experience in fraud or financial crime analytics, ideally in fintech, payments, or high-volume B2C.
• Hands-on experience designing, tuning, and evaluating rule-based detection, including trade-offs between catch rate, false positives, and customer friction.
• Advanced SQL and experience with modern data platforms and large-scale data processing, including distributed frameworks such as Spark or similar.
• Python experience for analysis and automation, including pandas, notebooks, scheduled workflows, and large datasets.
• Solid understanding of fraud typologies, AML/TF concepts, and emerging trends.
• Knowledge of Visa and Mastercard tools, data, and monitoring programs, including AVS, 3DS, chargeback, and fraud programs.
• Practical knowledge of payment methods including cards, tokenization, Apple Pay, and Google Pay.
• Experience building dashboards in Looker, Tableau, Power BI, or a similar BI tool.
• Ownership, clear communication, and documentation skills, with the ability to explain data-driven decisions to technical and non-technical stakeholders.

Nice to have

• Experience with rules engines, decisioning platforms, and expression-based rule logic.
• Experience applying statistical, unsupervised, or machine-learning anomaly detection to fraud or financial crime use cases.
• Familiarity with day-to-day financial crime operations.
• Experience working with auditors or regulators, or supporting regulatory reviews and partner due diligence.

Culture & Benefits

• Work in a global fintech focused on international money movement and products serving millions of customers.
• Ownership, autonomy, experimentation, continuous improvement, and fast execution are encouraged.
• Collaborate with colleagues from diverse backgrounds and disciplines across functions and geographies.
• Opportunities to learn, develop skills, take on new challenges, and advance across functions and geographies.

Hiring process

• Within the first three months, learn the products, detection framework, rules engine, data landscape, KPIs, tooling, and fraud and AML patterns; build cross-functional relationships and ship initial rule-tuning improvements.
• Within six months, co-own the rules lifecycle, launch KPI and activity tracking, and deliver an automation that removes recurring manual work.
• Within twelve months, contribute to detection effectiveness and reporting, deliver measurable improvements, and introduce new detection approaches and automation.