Data Scientist (Credit Risk)

TL;DR

Data Scientist (Credit Risk): Building application and behavioral credit scoring models for lending products with an accent on end-to-end model development, validation, deployment, and production monitoring. Focus on translating models into decision-engine logic, evaluating portfolio impact through NPV and backtesting, and improving approval strategies, cut-offs, and pricing.

Location: Remote from Kazakhstan, Georgia, or Serbia. Willingness to relocate to the Manila HQ is a strong advantage.

Company

hirify.global operates data-driven lending and credit products.

What you will do

• Build application and behavioral credit scoring models from scratch.
• Own the full modeling lifecycle, from data exploration and feature engineering through deployment and production monitoring.
• Validate models using AUC, KS, Gini, PSI, CSI, and bad-rate metrics.
• Evaluate business impact through NPV, backtesting, and real portfolio performance.
• Translate models into implementation-ready specifications for decision engines.
• Collaborate with product, engineering, and risk teams to refine approval strategies, cut-offs, pricing, and credit policy.

Requirements

• 2+ years of hands-on experience in credit risk modeling, rather than generic data science.
• Experience building or validating application and/or behavioral credit scoring models and understanding PD modeling.
• Strong Python, pandas, scikit-learn, and SQL skills.
• Experience with the full production model lifecycle, including monitoring, recalibration, and retraining.
• Experience with lending or credit products and real lending data such as bureau, transactional, or credit-history data.
• Ability to translate models into production decision-engine logic and evaluate portfolio business impact.

Nice to have

• Willingness to relocate to the Manila HQ.

Culture & Benefits

• Remote work from Kazakhstan, Georgia, or Serbia.
• Work is evaluated by measurable business value and real-world portfolio performance.
• High ownership and responsibility across the full model lifecycle.
• Close collaboration with product, engineering, analysts, and risk specialists.
• Exposure to credit data, user behavior, and market dynamics in a data-driven environment.