Xpetize - Fraud Data Scientist - Python/Power BI

Job Title : Fraud Data Scientist

Location : Bangalore

Experience : 3+ years

Employment Type : Full-time

Industry : Finance, FinTech, E-commerce, Banking, etc.

About The Role

We are seeking a highly analytical and detail-oriented Fraud Data Scientist with 3+ years of experience to join our Risk & Fraud Analytics team. In this role, you will leverage data science, machine learning, and domain expertise to detect, investigate, and prevent fraudulent activities across our platforms. You will play a critical role in safeguarding customer trust and minimizing financial losses.

Key Responsibilities

• Develop, implement, and maintain machine learning models for fraud detection and prevention.
• Analyze transactional, behavioral, and external data to identify fraud patterns and risk indicators.
• Partner with engineering and product teams to deploy models into production and monitor performance.
• Conduct root-cause analysis of fraud cases and propose scalable solutions to prevent

recurrence.

• Create dashboards, reports, and alerts to monitor key fraud KPIs and emerging threats.
• Work with stakeholders across risk, compliance, legal, and customer service to define fraud strategies.
• Continuously improve model accuracy, reduce false positives, and adapt to evolving fraud

tactics.

Required Qualifications

• 3+ years of experience in data science, analytics, or a similar role focused on fraud, risk, or trust & safety.
• Strong proficiency in Python, SQL, and machine learning libraries (e.g., scikit-learn, XGBoost, LightGBM).
• Experience with data visualization tools such as Tableau, Power BI, or Looker.
• Solid understanding of fraud typologies (identity theft, synthetic fraud, transaction fraud, etc.).
• Familiarity with real-time data pipelines and production model deployment (preferred: Spark,

Airflow, AWS/GCP).

• Strong problem-solving skills and the ability to work independently in a fast-paced

environment.

• Excellent communication skills with the ability to explain complex models to non-technical

stakeholders.

(ref:hirist.tech)