Senior Risk Analyst – Data Science & Analytics

Qualifications

• Approximately 5-8 years of relevant experience in credit-risk analytics, data science, decision science or statistical modelling, including at least 3 years of substantial experience in MSME / SME / commercial credit-risk or commercial bureau analytics.
• Advanced hands-on proficiency in Python and strong SQL, with demonstrated ability to build efficient, modular and reusable analytical code for large and granular credit datasets.
• Demonstrated end-to-end ownership of credit-risk scorecard or model development, from target and sample design through feature engineering, modelling, validation and implementation / monitoring considerations.
• Deep practical knowledge of scorecard and risk-model development, including binning, WoE / IV, logistic regression, variable selection, multicollinearity, reject-inference considerations where relevant, calibration, segmentation and score scaling, together with experience evaluating tree-based / gradient-boosting challengers.
• Strong command of validation and monitoring concepts including KS, Gini / AUC, lift / gains, calibration, out-of-time validation, back-testing, PSI / CSI, stability and challenger comparisons.
• Strong MSME credit-risk and bureau-data expertise: delinquency / default definitions, underwriting and segmentation, vintage / cohort and roll-rate analysis, early-warning indicators, and conversion of facility / tradeline histories into robust entity-level risk features.
• Experience delivering analytics for banks, NBFCs, fintechs or other business lenders, with the judgement to distinguish statistical results from commercially usable risk solutions.
• Strong client-facing and pre-sales capability, including discovery, solution framing, proof-of-concept design, methodology presentation and handling technical questions from senior risk / analytics stakeholders.
• Experience reviewing analytical work, coaching less-experienced analysts and improving team standards for code quality, validation, documentation and reproducibility.
• Direct experience developing or validating commercial credit bureau scores, bureau-based MSME risk models or other bureau-led decisioning solutions.
• Experience across multiple MSME lending products or lifecycle stages, such as business loans, working-capital facilities, secured / unsecured MSME credit, acquisition, underwriting, monitoring and collections.
• SAS or another statistical programming environment in addition to Python.
• Git, peer-review practices, Spark / Databricks or other tools used for large-scale analytical development.
• Experience taking risk models or analytics from proof of concept into production, including monitoring and challenger frameworks.
• Working knowledge of model-governance, credit-information and regulatory expectations relevant to lending in India.
• Experience shaping analytical propositions, reusable solutions or product enhancements from repeated client use cases.