D&B Technologies & Data Services
Website:
dnbtechnology.com
Job details:
Key Responsibilities
- Lead the design, development and validation of credit risk scorecard models using ML, AI, and other
statistical techniques, using Financial and Alternate Data.
- Perform advanced exploratory data analysis (EDA), feature engineering, and data preparation on large,
complex datasets
- Translate business and risk requirements into analytical solutions and support their integration into production systems. (e.g., AUC, KS, Gini)
- Own end-to-end model lifecycle: development, validation, deployment and ongoing monitoring
- Partner with engineering teams to integrate models into production systems (APIs, batch scoring, real-time decisioning) and collaborate with application teams to ensure robust and scalable implementation of scoring logic
- Develop monitoring frameworks, dashboards, and reports to track model performance, drift and portfolio health
- Produce high-quality technical documentation, validation reports, model reports and stakeholder presentations
- Provide technical guidance, best practices and task allocation to team members and support knowledge transfer across teams.
Required Technical Skills
Must Have
- 5–10 years of experience in ML models implementation & credit risk technology solutions
- Deep understanding of statistical modelling techniques (logistic regression, WOE/IV, binning, model validation) and machine learning methods
- Strong proficiency in Python (preferred) or similar analytical tools (e.g., SAS, STATA)
- Advanced SQL skills and experience working with large-scale relational databases (e.g., Oracle, SQL Server, Postgres and MongoDB)
- Experience managing analytics or technology delivery projects
- Strong communication skills
Good to Have
· Basic understanding of credit risk modelling / scorecard concepts
· Familiarity with BI and visualization tools such as Power BI
· Knowledge of regulatory frameworks in credit risk (e.g., IFRS 9, Basel III)
· Experience with cloud platforms (AWS, Azure, or GCP)
Impact
· Drive credit risk strategy through robust, production-grade models
· Improve portfolio performance and decision accuracy
· Shape best practices in model development, deployment, and monitoring.
Click on Apply to know more.