Role Overview

We are looking for a highly skilled Data Scientist to join the Machine Learning Model Development & Integration program within Financial Crime Technology.

In this role, you will design, develop, and optimise machine learning models that enhance detection accuracy across Anti Money Laundering (AML), Fraud, Transaction Monitoring, and Customer Behaviour Analytics.

You will collaborate closely with Data Engineers, ML Engineers, SMEs, and Product teams to build models that are accurate, explainable, performant, and compliant with regulatory standards such as PRA SS2/21.

Skills & Experience Required- Technical Skills

Solid proficiency in Python, ML libraries (scikit-learn, XGBoost, PyTorch/TensorFlow), and statistical modelling.

Experience building and evaluating models for structured and unstructured data.

Hands-on familiarity with cloud ML platforms (preferably AWS SageMaker).

Strong foundations in statistics, probability, and algorithmic understanding.

Experience with MLOps tools such as MLflow, Weights & Biases, or SageMaker Pipelines (desirable).

SQL expertise and comfort working with large datasets.

Domain/Platform Skills

Knowledge of financial crime, AML typologies, KYC, sanctions, or fraud analytics (preferred but not mandatory).

Understanding of model risk, explainability, fairness, data drift, and model monitoring frameworks.

Soft Skills

Ability to translate complex technical results into actionable business insights.

Key Responsibilities-

- Model Development & Experimentation

Develop/integrate supervised, unsupervised, and semi supervised ML models for financial crime detection. Apply advanced techniques such as graph analytics, anomaly detection, NLP, temporal modelling, and risk scoring.

Conduct data exploration, hypothesis testing,



feature selection, and feature engineering.

Build training and validation datasets aligned with model governance requirements.

- ML Research & Innovation

Experiment with cutting-edge algorithms and deep learning architectures where appropriate. Evaluate model sensitivity, stability, drift, and performance in real-world environments.

Explore new techniques such as explainable AI (SHAP/LIME/Counterfactuals) for model transparency.

- Model Integration & Operationalisation

Work with ML Engineers and Data Engineers to integrate models into production systems (batch & real-time). Support deployment on platforms such as AWS SageMaker, EKS/ECS, or custom microservices.

Contribute to establishing standardised frameworks for model versioning, monitoring, and retraining.

- Data Collaboration & Feature Engineering

Partner with Data Engineers to shape high-quality, reliable features for training and inference. Contribute to the design of feature stores, lineage standards, and data quality controls.

Ensure reproducibility through robust data handling, documentation, and experimentation tracking.

- Model Governance, Explainability & Compliance

Document models end-to-end: purpose, assumptions, data sources, limitations, validation strategies. Support independent model validation and regulatory reviews.

Ensure alignment with regulatory requirements (e.g., PRA SS2/21, internal MRM frameworks).

- Cross-functional Collaboration

Work with SMEs, analysts, and investigators to interpret model outputs and business impact. Present findings to leadership in a clear and concise manner.

Participate in Agile ceremonies and contribute to program level planning.

Location - Chennai, Bangalore, Pune, Hyd, New Delhi, Kolkata

Experience Required: 6+ years

📌 Data Scientist (Chennai)
🏢 VMC Soft Technologies
📍 Chennai