Fintech Fraud & Risk Analytics Engineer

Location: Gurgaon / Remote (Hybrid / Flexible Work Policy)

Employment Type: Full time

Experience Required: 3–5 Years

Industry-Standard Salary Range: 18 LPA – 32 LPA

About Us & Our Mission

In the fast-paced ecosystem of digital B2B fintech settlement rails and cross-border payments, financial fraud attempts are increasingly sophisticated and executed in milliseconds. Protecting enterprise ledger systems and merchant accounts requires real-time anomaly detection, sophisticated graph analysis, and instantaneous risk scoring.

Our engineering culture values proactive threat mitigation, high-performance data processing, and uncompromised system reliability. If you want to build intelligent risk engines that protect multi-million-dollar financial networks from malicious actors, you will find your professional home with us.

The Role & Impact

We are seeking a sharp, data-driven Fintech Fraud & Risk Analytics Engineer to design, build, and deploy real-time fraud detection and risk scoring systems. In this role, you will analyze massive transaction streams, build behavioral profiling models, and implement automated rules and machine learning classifiers that flag suspicious activities before settlement occurs. You will work at the critical intersection of data science, backend engineering, and financial security.

Key Responsibilities & Daily Expectations

- Risk Engine Development: Design and scale real-time transaction screening microservices and rule evaluation engines using Python, FastAPI, and asynchronous message queues.

- Feature Engineering:



Build and maintain low-latency feature stores that compute rolling user velocity, device fingerprinting, and transactional behavioral anomalies on the fly.

- Model Integration: Integrate machine learning classification and anomaly detection models (Isolation Forests, XGBoost, graph-based link analysis) directly into payment processing pipelines.

- Investigation Dashboards: Build analytical reporting tools and investigative dashboards for compliance teams to review flagged transactions and audit fraud patterns.

- Latency Optimization: Ensure fraud evaluation checks execute well within tight SLA windows (under 50 milliseconds) to prevent payment friction.

What We Are Looking For (Requirements)

- Experience: 3 to 5 years of professional experience in data engineering, machine learning engineering, or backend development within fintech, banking, or risk management domains.

- Technical Mastery: Strong command of Python, advanced SQL, and experience with streaming data platforms (Kafka/Flink) and relational/NoSQL datastores.

- Domain Knowledge: Solid understanding of payment gateway flows, anti-money laundering (AML) indicators, KYC verification logic, and common fintech fraud vectors.

- Analytical Mindset: Proven ability to analyze large datasets, spot statistical anomalies, and tune precision/recall tradeoffs for risk models.

- Education: Degree in Computer Science, Statistics, Mathematics, or equivalent analytical field.

What We Offer & How to Apply

- Competitive Compensation: Industry-standard salary bracket (18–32 LPA) backed by performance bonuses and equity options.

- High-Impact Role: Direct ownership over core financial security and fraud prevention systems.

📌 Fintech Fraud & Risk Analytics Engineer (Gurugram)
🏢 HyrEzy Talent Solutions
📍 Gurugram