Data Scientist

About the Role:

We are looking for a passionate and results-driven Data Scientist with 2–3 years of experience to join our data science team. This role involves building robust machine learning and deep learning models for high-impact financial use cases such as fraud detection, risk scoring, personalization, and automation.

You should have strong Python programming skills, hands-on experience with end-to-end ML/DL model development, MLOps deployment, Experience building and exposing APIs for model interaction and integration with production systems is essential.

Key Responsibilities:

•Design, develop, and deploy ML/DL models for FinTech use cases (e.g., fraud detection, customer risk classification, churn prediction).

•Handle and process large, highly imbalanced datasets using advanced resampling, cost-sensitive learning, or anomaly detection techniques.

•Implement and automate MLOps pipelines for training, testing, monitoring, and deploying models to production (e.g., using MLflow or Kubeflow).

•Build APIs and backend interfaces for seamless model consumption in production applications.

•Collaborate closely with Data Engineers, Product Managers, and Frontend Developers to operationalize ML solutions.

•Document model assumptions, performance metrics, and testing methodology for audit and compliance readiness.

•Contribute to continuous model monitoring and re-training pipelines to ensure production accuracy and relevance.

•Stay current on emerging ML and GenAI techniques (exposure to GenAI is a plus but not mandatory).

Key Requirements:

•2–3 years of hands-on experience in data science/machine learning/Deep Learning developer role.

•Domain experience in FinTech, payments, or financial services (mandatory).

•Proficiency in Python and popular ML/DL libraries: scikit-learn, XGBoost, TensorFlow, PyTorch.

•Experience with model deployment, Docker, FastAPI/Flask, and building APIs.

•Experience with MLOps tools (e.g., MLflow, DVC).

•Strong knowledge of data preprocessing, feature engineering, and model evaluation

•Familiarity with version control (Git), CI/CD workflows, and agile practices.

•Strong communication and documentation skills.