You're using an older version of Internet Explorer that is no longer supported. Please update your browser.

Data Scientist I, AI/ML Model Testing Automation Developer

Toronto, ON
Full Time
3 days ago
Company Overview

Tell us your story. Don't go unnoticed. Explain why you're a winning candidate. Think "TD" if you crave meaningful work and embrace change like we do. We are a trusted North American leader that cares about people and inspires them to grow and move forward.

Stay current and competitive. Carve out a career for yourself. Grow with us. Here's our story:

Department Overview
TD Model Validation (MV) group is responsible for the independent validation and approval of analytical models used for risk, pricing, hedging, insurance, marketing, fraud and capital evaluation for portfolio of financial products. This also includes validation of decision making models.

Job Description

The position reports to AVP, AI/ML Model Validation (MLMV) group within MV. Detailed accountabilities include:
  • Develop and implement an automation tool/platform/dashboard for Machine Learning model validation testing and analysis. The successful candidate will be involved first-hand in and leading the development of automation efforts for the MLMV group. The candidate will be responsible for implementing the standardization and automation of the validation tests performed by the MLMV Data Scientists for the validation/vetting of AI/ML models. This includes:
    • Writing and maintaining code repository leveraging existing code (used for model performance testing, model explainability analysis, data analysis, etc.) to produce standardized output such as tables, figures and plots for validation reports.
    • Creating automated porting of the standardized MV testing results/outputs into a Word validation report template.
    • Creating a dashboard/app that will serve as the GUI for the above automated tests to be used by MLMV Data Scientists.

The candidate may also be involved in daily MLMV model validation projects where the tasks include
  • Validate (review and provide effective challenge) Machine Learning models and AI applications.
  • Implement Machine Learning model validation methodologies and standards. Ensure that the validation methodologies and standards are in line with industry best practice or address regulatory and audit requirements and/or findings in a timely manner.
  • Apply a variety of statistical tests and modeling techniques to identify/recommend improvements to models and undertake related initiatives. Ensure extensive testing of model sensitivity that help assessing model behavior and risk.
  • Implement and evaluate external models used for benchmarking internal model performance. Participate in model selection and related due diligence activity.
  • Maintain full professional knowledge of techniques and developments in the field of Data Science and Machine Learning, and share knowledge with business partners and senior management.

The position involves working effectively with different internal partners such as TD Wealth, TD Insurance, ED&A, PBSA, Layer6 and etc.


  • Strong quantitative and programming skills with an advanced degree in one or more of the following areas: computer science, mathematics, physics, statistics, machine learning, engineering, and/or actuarial science.
  • Up to 3 years' experience of working in analytical environments. Specifically, in development of automation tools / platforms for Data Science tasks.
  • Up to 3 years' experience of developing automation tools, software packages and desktop or web browser based analytical applications.
  • Proficient in one or more programming languages such as Python, Java, R, or other OOP languages.
  • Expertise in R Shiny, Dash/Plotly or other browser-based dashboard development tools, or desktop application development tools (TKinter etc.).
  • Experience with working in Linux shell environment and virtual machines / remote servers.
  • Experience with and knowledge of Machine Learning theory and predictive algorithms: Bagging and Gradient Boosting methods (XGBoost), Neural Networks/Deep Learning, NLP, Bayesian/probabilistic methods and etc.
  • Experience with and knowledge of Machine Learning Model Interpretation/Explanation methods and algorithms, such as Shapley (SHAP), PDP, Permutation Feature Importance, LIME, ELI5 and etc.
  • Experience with Big Data analytics tools and environments, such as, Microsoft Azure, Hadoop/Hive and Spark (or pySpark).
  • Ability to research and implement Machine Learning and statistical algorithms from academic research papers is a plus.
  • Excellent verbal and written communication skills (position requires writing reports).
  • Quick learner who constantly works on improving their skills and expertise.
  • Good time management and multitasking skills with minimal supervision.



At TD, we are committed to fostering an inclusive, accessible environment, where all employees and customers feel valued, respected and supported. We are dedicated to building a workforce that reflects the diversity of our customers and communities in which we live and serve. If you require an accommodation for the recruitment/interview process (including alternate formats of materials, or accessible meeting rooms or other accommodation), please let us know and we will work with you to meet your needs.
Banking, Finance and Insurance