Job
Description
You are a highly skilled and experienced Machine Learning Modeling Lead being sought to join the ML Model Innovation team in the banking domain, particularly in retail transactional and lending areas. Your main responsibility will be to lead the development and deployment of machine learning models that drive crucial business decisions such as collections models, credit risk scoring, fraud detection, customer segmentation, and personalized financial services. You are required to possess a strong understanding of banking business, data, and domain, covering the customer lifecycle as well as bureau/external data. Collaboration with cross-functional teams and providing technical leadership to other ML modelers and data scientists is a key part of the role. With a minimum of 8 years of experience in Retail banking, you should have deep business expertise in different business lines within the Credit risk space across the customer lifecycle. An in-depth knowledge of banking strategies related to Underwriting, Collection & Recoveries, High-Risk Account Management (HRAM), and ECM Strategies is essential. Additionally, familiarity with Fraud strategy and analytics in the Retail banking domain is advantageous. Your expertise should cover end-to-end hands-on ML solution development, including data exploration, feature engineering, model development, validation, deployment, and monitoring. Developing robust models to solve various business problems and drive business benefits is a core responsibility, along with supporting and reviewing junior data scientists" submissions and providing enhancement suggestions. Documentation, model reviews, submission reviews, managing queries from model validation teams, and defending models/solutions against internal MRM/audit teams are part of your duties. You will collaborate with implementation teams to deploy models into production environments, whether cloud or on-premise. Working closely with business stakeholders to translate banking domain challenges into data-driven solutions is crucial. Guiding junior data scientists and engineers on best practices in model development and MLOps, continuously evaluating new tools, technologies, and frameworks relevant to ML in finance, publishing internal research, and promoting a culture of innovation and experimentation are also key aspects of your role. Your educational background should include a Masters or similar degree in Computer Science, Data Science, Statistics, Applied Mathematics, or a related quantitative field. You should have strong business knowledge of banking analytics across the retail banking customer lifecycle. With over 8 years of experience in applied machine learning model development in banking or financial services, hands-on experience leading ML projects and teams, expertise in model development, deployment, and monitoring in production environments, and familiarity with underwriting, collections, ECM, fraud, and ethical considerations in banking ML models, you are well-equipped for this role. In terms of skills, you should be an expert in Python, SQL, ML libraries (Numpy, Pandas, Scikit-learn, TensorFlow, PyTorch), and techniques such as Regression, Decision Trees, Ensembles (XGBoost, GBM, Random Forest, Unsupervised Learning, etc.). Knowledge of MLOps frameworks (MLflow, Kubeflow, Airflow, Docker, Kubernetes) is a plus. A strong grasp of statistical modeling, optimization, and deep learning techniques, along with excellent communication skills and the ability to explain complex concepts to non-technical stakeholders, are essential for success in this position.,
