Iris Software is looking to hire a Data Scientist / ML Engineer for a full-time opportunity in Toronto, ON (hybrid position).

Job Title: Data Scientist / ML Engineer Full-time with Iris Software for one of the banks in downtown Toronto data wrangling Tool stack probably in this order - Python, PySpark, Glue, Sagemaker, SAS Foundation & Feature Engineering : Lead the foundational setup of Python/PySpark development environments, actively managing complex package dependencies and virtual environments using Conda/Anaconda.

Pipeline Development : Design, build, and deploy net-new data pipelines focused heavily on feature engineering and data preparation to feed downstream machine learning and analytics use cases. Analyze and reverse-engineer existing SAS programs (developed by business users and data scientists) to accurately extract business rules, data transformations, and calculations.

Performance Tuning : Optimize PySpark code for performance, scalability, and maintainability within distributed data processing environments.

Stakeholder Collaboration : Collaborate closely with business users and data scientists to clarify requirements, validate feature outputs, and resolve discrepancies during the migration process.

Quality Assurance : Perform robust unit testing, data reconciliation, and automated validation to ensure absolute data parity between legacy SAS outputs and the new PySpark pipelines. Document technical designs, code lineage, testing results, and migration methodologies for future team scaling. Strong programming expertise in Python and PySpark for distributed data processing.

Proven experience building data pipelines specifically for feature engineering,



data curation, and advanced data preparation. Ability to read, interpret, and reverse-engineer legacy SAS code (such as SAS data steps, procedures, and macros) to extract complex business logic. (Experience establishing and managing Python environments, ensuring reproducibility, and handling library dependencies using Anaconda/Conda. Advanced SQL skills and experience working with large-scale structured datasets.

Experience working with cloud-based data platforms (Azure, AWS, or GCP). Familiarity with version control tools (Git) and collaborative development workflows.

Experience with CI/CD pipelines, automated testing, and MLOps principles. Knowledge of data governance, data cataloging, and data quality best practices. Python & PySpark Agile Delivery About Iris Software Inc. and Canada, Iris Software delivers technology services and solutions that help clients complete quick, far-reaching digital transformations and achieve their business goals.

A strategic partner to Fortune 500 and other top companies in financial services and many other industries, Iris provides a value-driven approach - a unique blend of highly skilled specialists, software engineering expertise, cutting-edge technology, and flexible engagement models. High customer satisfaction has translated into long-standing relationships and preferred-partner status with many of our clients, who rely on our 30+ years of technical and domain expertise to future-proof their enterprises. Associates of Iris work on mission-critical applications supported by a workplace culture that has won numerous awards in the last few years, including Certified Great Place to Work in India;

📌 Data Scientist / ML Engineer (Toronto)
🏢 Iris Software
📍 Toronto