Assistant Manager – Data Science

Job Description:

We are looking for a highly motivated and skilled ML Lead for the development and maintenance of advanced machine learning models for financial client, esp. in payments and risk to join our growing team.

Responsibilities:

1.   Building and Deploying Machine Learning Models:

·        Develop, train, and deploy machine learning models to predict fraud and manage merchant risk.

·        Utilize supervised learning techniques (e.g., Logistic Regression, Decision Trees, XGBoost, LightGBM) to build risk models for assessing merchant creditworthiness.

·        Leverage deep learning models (e.g., Neural Networks, Recurrent Neural Networks) to detect fraud at onboarding and during various stages of merchant interactions.

·        Build and maintain predictive models for fraud detection that assess risk in real time, enabling fraud prevention at the point of transaction.

2.   Advanced Model Development:

·        Apply state-of-the-art ML techniques including deep learning, reinforcement learning, and graph-based models (e.g., knowledge graphs, Neo4j, Memgraph) for detecting complex fraud patterns.

·        Work with Neural Networks (e.g., Feedforward, Convolutional, Recurrent) for sequence modeling and time-series forecasting.

·        Design and implement Generative AI solutions to process large volumes of unstructured data (e.g., customer reviews and feedback) using Transformer models such as GPT.

3.   Merchant Underwriting and Creditworthiness Assessment:

·        Develop models for merchant underwriting that assess a merchant’s legitimacy and ability to process payments securely.

·        Build supervised learning models to provide propensity scores to assess merchant creditworthiness, ensuring business legitimacy.

·        Utilize AWS Sage maker, Snowflake, and SQL for model development and data preparation.

4.   Time-Series Forecasting for Loss Prediction:

·        Build and maintain advanced time-series models (e.g., ARIMA, SARIMA, Prophet, ETS) for loss forecasting and assessing the financial impact of fraud, chargebacks, and other risks.

·        Perform scenario and what-if analysis to optimize risk strategy and minimize losses.

 Skills:

·        Strong proficiency in Python for developing ML models and data manipulation (e.g., Pandas, NumPy).

·        Expertise in machine learning frameworks such as TensorFlow, PyTorch, and Scikit-learn.

·        Experience with deep learning architectures like Neural Networks, RNNs, and Transformer models.

·        Familiarity with graph databases (e.g., Neo4j, Memgraph) and applying centrality measures and clustering for fraud detection.

·        Proficiency with cloud platforms like AWS (especially AWS Sagemaker) and Snowflake for model deployment and data management.

·        Solid understanding of SQL for data extraction and manipulation.