Senior Data Scientist

Qfin; Toronto; On-site; CAD 120,000 - 180,000; Full time

Benefits offered by this job

Flexible work model

Health benefits

Learning budget

Job summary

Qfin is seeking a Senior Credit Risk Modeling – Data Science expert to independently develop, validate, and maintain predictive credit risk models for unsecured personal lending. You will collaborate with data science, risk, and business teams to optimize risk strategies and enhance credit decisioning.

You will lead model development, validation, and governance, mentor junior analysts, and contribute to building a strong analytical culture within the team.

Qualifications

• Bachelor’s or Master’s degree in Statistics, Mathematics, Economics, Data Science, or a related quantitative field.
• 5–7 years of experience in credit risk modeling within a lending environment.
• Strong expertise in statistical modeling, machine learning, and predictive analytics (e.g., logistic regression, decision trees, gradient boosting, neural networks).

Responsibilities

• Lead the development of credit risk predictive models (PD, LGD, EAD, propensity to default, credit scoring).
• Conduct in-depth data analysis and feature engineering to improve model performance.
• Validate, back-test, and monitor models to ensure predictive accuracy and regulatory compliance.
• Partner with business and operations to integrate model outputs into lending strategies.
• Develop and maintain documentation for model development, validation, and governance.

Skills

Statistical modeling

Machine learning

Predictive analytics

Python

R

SAS

SQL

Credit risk concepts

Education

Bachelor’s or Master’s degree in quantitative field

Job description

As a Senior Credit Risk Modeling – Data Science, you will be an individual contributor responsible for developing, validating, and maintaining predictive credit risk models for our unsecured personal lending products. You will work closely with data science, risk, and business teams to optimize risk strategies and enhance the overall credit decisioning framework.

Key Responsibilities

• Lead the development of credit risk predictive models (e.g., PD, LGD, EAD, propensity to default, credit scoring models) for lending business.
• Conduct in-depth data analysis and feature engineering using internal and external data sources to improve model performance.
• Validate, back-test, and monitor existing credit risk models to ensure predictive accuracy and regulatory compliance.
• Partner with business and operations teams to integrate model outputs into lending strategies and decisioning processes.
• Develop and maintain documentation for model development, validation, and governance purposes in line with regulatory expectations.
• Provide insights on portfolio risk trends, early warning indicators, and potential loss drivers.
• Mentor junior analysts and contribute to building a strong modeling and analytical culture within the team.

Required Qualifications & Experience

• Bachelor’s or Master’s degree in Statistics, Mathematics, Economics, Data Science, or a related quantitative field.
• 5–7 years of experience in credit risk modeling within a lending environment.
• Strong expertise in statistical modeling, machine learning, and predictive analytics (e.g., logistic regression, decision trees, gradient boosting, neural networks).
• Proficiency in programming languages such as Python, R, or SAS; SQL experience essential.
• Solid understanding of credit risk concepts, portfolio management, and lending business processes.
• Excellent problem-solving, communication, and stakeholder management skills. Preferred Skills

Preferred

• Experience with cloud-based data platforms or modern analytics tools.
• Familiarity with alternative data usage in credit risk models.
• Exposure to model governance and audit processes in regulated financial institutions.
• Experience with model validation frameworks and regulatory compliance requirements in Canada (OSFI) or equivalent international standards.

What We Offer

• Competitive base salary + performance bonus + equity package.
• Fast-growth startup environment with direct impact on product and P&L.
• Flexible work model (hybrid/remote options).
• Learning budget, health benefits, and team culture focused on data and innovation.