Modelling / Forecasting Senior Analyst (Quants)

TD•Toronto, ON

3d•CA$81,600 - CA$115,200•Onsite

About The Position

The Non-Retail Model Development (NRMD) group is responsible for methodology development related to credit risk and operational risk in non-retail Wholesale and Commercial businesses. These methodologies cover Basel III credit parameters, including PD, LGD, and EAD/UGD, regulatory and economic capital for AIRB credit risk, IFRS 9 allowances, and Risk Ratings. Model Development is responsible for developing mathematical methodologies, building software prototypes, and working closely with other functions throughout the bank to implement system solutions. The U.S. Non-Retail Model Development team focuses on developing, enhancing, and implementing credit risk methodologies for U.S. Commercial portfolios, including Point-in-Time risk parameter models, CECL/IFRS 9 allowance methodologies, and stress testing / forecasting frameworks. The team partners closely with Risk, Finance, Technology, Model Validation, and Governance stakeholders to deliver robust, forward-looking credit risk solutions that support business decision-making, regulatory requirements, and risk management objectives. As a Senior Quantitative Analytics Analyst, you will contribute to the development, enhancement, monitoring, and implementation of credit risk parameter models and stress testing / forecasting methodologies for U.S. Commercial portfolios. The role supports Point-in-Time PD, LGD, and EAD models, CECL/IFRS 9 allowance methodologies, and scenario-based forecasting frameworks. You will work with complex commercial credit datasets, evaluate model performance and limitations, develop scalable analytical tools, and help translate quantitative insights into clear documentation and stakeholder-ready recommendations. This position provides excellent learning and career opportunities in a highly professional and motivated team environment, with exposure to high-impact U.S. Commercial portfolio modeling initiatives, senior stakeholders, evolving regulatory expectations, and opportunities to develop deep expertise in credit risk model development, forecasting methodologies, advanced analytics, and modern modeling technologies.

Requirements

Graduate degree in Statistics, Mathematics, Financial Engineering, Economics, Data Science, Computer Science, or another quantitative discipline.
Experience or strong academic exposure in credit risk modeling, loss forecasting, econometric modeling, statistical modeling, or related quantitative analysis.
Knowledge of credit risk parameters and frameworks, including PD, LGD, EAD, CECL/IFRS 9, stress testing / forecasting, and Basel capital concepts.
Strong programming and data analysis skills, preferably in Python and SQL; experience with SAS, R, MATLAB, or similar tools is an asset.
Experience working with complex datasets and applying quantitative methods to support model development, testing, monitoring, or reporting.
Strong analytical, problem-solving, written communication, and verbal communication skills.
Demonstrated initiative, attention to detail, and ability to deliver high-quality analytical work within defined timelines.
Familiarity with model risk management, data governance, automation, machine learning, or AI-enabled productivity tools is an asset.

Nice To Haves

Demonstrated ownership mindset, curiosity, and ability to independently progress assigned analytical workstreams in complex or ambiguous environments.
Experience improving analytical workflows through automation, reusable code, standardized templates, or scalable reporting solutions.
Exposure to machine learning, advanced analytics, or AI-enabled tools, with practical understanding of explainability, documentation, governance, and model risk considerations.
Ability to identify model, data, process, or documentation gaps and recommend practical enhancements.
Strong communication skills with ability to translate quantitative analysis into actionable insights, limitations, and recommendations.
Willingness to constructively challenge legacy approaches and contribute to innovative, controlled, and regulator-friendly model development practices.

Responsibilities

Support the design, development, enhancement, testing, implementation, and monitoring of Point-in-Time PD, LGD, and EAD models, CECL/IFRS 9 allowance methodologies, and stress testing / forecasting models for U.S. Commercial portfolios.
Develop and enhance credit risk stress testing and forecasting methodologies, including scenario analysis, macroeconomic driver assessment, sensitivity testing, attribution analysis, and impact assessment.
Conduct quantitative analysis to support model development activities, including data preparation, segmentation, feature construction, variable assessment, model estimation, calibration, benchmarking, sensitivity analysis, back-testing, attribution analysis, and impact assessment.
Build, maintain, and improve reusable analytical tools, scalable code-based workflows, and reporting capabilities to support model development, testing, monitoring, documentation, and implementation activities.
Analyze portfolio characteristics and modeling challenges associated with U.S. Commercial portfolios, including data limitations, portfolio heterogeneity, obligor concentration, economic cyclicality, low-default behavior, and expert judgment considerations where applicable.
Assess model performance through monitoring, diagnostics, sensitivity testing, back-testing, and evaluation of emerging risk drivers, and recommend enhancements where appropriate.
Prepare clear and well-structured model documentation, technical analyses, presentations, and supporting materials that explain methodology, assumptions, limitations, results, and business implications to both technical and non-technical audiences.
Support compliance with TD Model Risk Management standards, relevant regulatory expectations, and Data Governance requirements, including documentation of assumptions, limitations, controls, model performance metrics, and data quality considerations.
Contribute to model enhancements, redevelopment activities, and new model development initiatives, while identifying opportunities to improve methodologies, analytical processes, documentation standards, and recurring reporting workflows through automation and scalable solutions.
Partner with stakeholders across Risk, Finance, Technology, Governance, Model Validation, and Business teams to support model development, review, implementation, issue remediation, and ongoing model use.
Evaluate and recommend enhancements to legacy methodologies, processes, and analytical approaches while balancing model performance, interpretability, governance requirements, and implementation considerations.
Contribute to research and controlled experimentation involving advanced analytics, machine learning, and AI-enabled tools where appropriate, while considering explainability, documentation, governance, and model risk requirements.