Location : Gurgaon

Notice Period : Immediate joiners preferred (within 15 days)

Domain : Financial Crime & Fraud Analytics

Role Overview :

We are seeking a highly skilled Data Scientist with strong expertise in fraud detection and financial crime analytics. The ideal candidate will be responsible for delivering end-to-end machine learning solutions, from problem formulation to model deployment, to detect anomalies, prevent fraud, and strengthen risk management frameworks.

Key Responsibilities :

- Develop and implement machine learning models for fraud detection, risk scoring, and anomaly detection

- Work on end-to-end ML lifecycle including data collection, feature engineering, model training, validation, and deployment

- Apply advanced algorithms such as XGBoost, Random Forest, and other ensemble models for predictive analytics

- Analyze large and complex datasets to identify fraud patterns, suspicious behaviors, and emerging risks

- Collaborate with business, risk, and compliance teams to translate requirements into scalable data science solutions

- Deploy models into production and monitor performance, ensuring accuracy and stability over time

- Perform model tuning, validation, and performance optimization

- Build reusable, scalable ML pipelines and frameworks

- Work with structured and unstructured data sources to enhance model effectiveness

- Communicate insights and findings clearly to both technical and non-technical stakeholders

Required Skills & Qualifications :

- 6- 9 years of experience in Data Science / Machine Learning roles

- Strong proficiency in Python programming (NumPy, Pandas, Scikit-Learn, etc.)

- Hands-on experience with :

1. Machine Learning algorithms (XGBoost, Random Forest, Gradient Boosting, etc.)

2. Fraud Detection / Financial Crime Analytics use cases

- Experience in end-to-end ML project delivery

- Strong expertise in model development, evaluation, and deployment

- Solid understanding of statistics, probability, and data modeling techniques

- Experience working with large-scale datasets

- Knowledge of data preprocessing, feature engineering, and model explainability

- Strong analytical thinking and problem-solving skills

Preferred Qualifications :

- Experience in Banking / Financial Services / FinTech domain, especially fraud and risk

- Familiarity with real-time fraud detection systems

- Exposure to big data technologies (Spark, Hadoop)

- Experience with model deployment tools (Docker, APIs, MLOps frameworks)

- Knowledge of regulatory compliance and risk frameworks in financial services