
Principal Data Scientist
- Toronto, ON
- Permanent
- Full-time
- Be a senior practitioner researching and building production quality fraud models that run in real time to screen transaction networks
- Work closely with the business owners to understand business requirements, performance metrics regarding data quality and model performance of customer facing products
- Work with multiple disparate sources of data, storage systems, and build processes and pipelines to provide cohesive datasets for analysis and modelling
- Generate and maintain and optimize data pipelines for model building and model performance evaluation
- Set the roadmap and identify methods and approaches that enhances the performance of existing fraud detection models
- Overall responsibility for development, testing, and evaluation of modern machine learning and AI models for specific products
- Oversee implementation of models
- Evaluate production models based on business metrics to drive continuous improvement
- Extensive data science experience and significant leadership roles
- Demonstrated full lifecycle model development, deployment and evaluation for complex problems
- Experience with SQL language and the following technologies: PySpark, Hadoop, Databricks
- Good knowledge of Linux / Bash environment
- Solid Python skills
- Familiarity with XGBoost
- Strong communication skills
- Highly skilled problem solver
- Exhibits a high degree of initiative
- At least an undergraduate degree in CS, or a STEM related field
- PhD/Master’s in CS, Data Science, Machine Learning, AI or a related STEM field
- Experience in with data engineering and model building in PySpark using Spark ML on petabyte scale data
- Understands and implements methods to evaluate own work and others for bias, inaccuracy, and error
- Loves working with error-prone, messy, disparate, unstructured data