About You:You thrive in a vibrant, entrepreneurial organization where your ideas are valued. You are motivated by goals, a self-starter, and enjoy wearing multiple hats in a fast-growing fintech environment.
You are a builder at heart-someone who prefers creating reliable data pipelines over another dashboard. You thrive on owning the "plumbing" that delivers clean, timely data to machine learning models and enjoy turning manual, messy processes into repeatable automation. As the Analytics Engineer, Risk, you'll join the Model Development team within Risk, working closely with the Manager, Model Development, Data Scientists, and Model Developers. This highly technical, hands-on role focuses on the data infrastructure supporting credit risk models, including ETL pipelines for model training and scoring, standardized ingestion of new data sources-including UK data-and day-to-day delivery of stable production data. You'll work primarily in Python and SQL with tabular, time-series, and, as we grow, graph-structured data such as Neo4j.
Responsibilities- Own the integration of new data sources, into Propel's model-ready data standards, ensuring consistent schemas, definitions, and quality across regions (CA/US/UK)
- Design, build, and maintain ETL pipelines that prepare and deliver data for model training, retraining, and scoring across multiple model types, including survival, classification, and regression models
- Build and maintain pipelines within the shared ETL/orchestration framework for model development, following the templates and patterns established by the Model Development team so new models can be onboarded quickly
- Build feature engineering and data transformation logic for tabular and time-series data, using tools such as tsfresh or similar
- Monitor the health and stability of data pipelines feeding models in production; proactively identify and resolve data drift, quality issues, and pipeline failures
- Write clean, well-tested, production-grade Python code, including scripts and reusable packages or modules, that other team members can build on
- Work with containerized model deployments using Docker and Kubernetes, as well as cloud infrastructure such as AWS and S3 for data storage and workflow orchestration, with support from our Infrastructure team
- Query and transform data from relational databases and data warehouses using SQL.
- Document data sources, pipeline logic, and transformations clearly so pipelines are auditable, maintainable, and easy to hand off
- Collaborate closely with Data Scientists and Model Developers to translate model requirements into scalable, production-ready data pipelines, and with the Business Analytics Engineering and Infrastructure teams where pipelines intersect with broader data platform work
RequirementsMust Have- Bachelor's degree in computer science, data engineering, statistics, mathematics, or a related quantitative field
- Minimum of 3 years of hands-on Python skills and comfortable writing production-quality, testable, reusable code
- Familiarity with common data and ML libraries such as pandas, NumPy, and scikit-learn
- Experience building or maintaining ETL or data pipelines
- Experience with pipeline or workflow orchestration tools such as Metaflow, Airflow, Prefect, Dagster, or similar is a plus
- Comfortable working with different data shapes: tabular and time-series data
- Solid SQL skills for querying and transforming data into relational databases such as MySQL and/or data warehouses
- Understanding of the ML data lifecycle, including feature engineering, training and scoring data preparation, and model monitoring and drift concepts
- Experience with version control using Git and basic CI/CD practices
- Strong communication and collaboration skills, with the ability to work closely with Data Scientists, Model Developers, and Infrastructure/Engineering stakeholders
- Experience in fintech, credit risk, or another regulated or data-intensive industry is a plus
- Experience using generative AI tools such as ChatGPT, Claude, or Copilot to accelerate day-to-day engineering work is an asset
Nice to Have- Exposure to graph data or graph databases such as Neo4j (nice-to-have)
- Snowflake experience (nice-to-have)
- Exposure to Docker, containerization, and cloud infrastructure such as AWS, S3, EKS, or similar services (nice-to-have)
Benefits to Joining Propel- Growth and opportunity - we pride ourselves on promoting from within
- Incredible company culture
- Competitive salary and health benefits
- Comprehensive vacation package
- Group health and dental benefits
- Group RRSP program
- Support for new parents
- Diverse and inclusive workplace
Salary Range$70,000 - $100,000
Final compensation is determined by market conditions, location, and the candidate's experience, skills, and education. This role may also be eligible for performance-based incentive programs and total compensation may include variable incentives, such as bonuses and commissions.
This posting is for an existing vacancy within our organization. 
