Backend Python Engineer with Machine Learning at Smooth Commerce
Toronto, ON M5H 2R2, Canada -
Full Time


Start Date

Immediate

Expiry Date

09 Dec, 25

Salary

115000.0

Posted On

10 Sep, 25

Experience

2 year(s) or above

Remote Job

Yes

Telecommute

Yes

Sponsor Visa

No

Skills

Validation, Communication Skills, Aws, Scalability, Handover, Data Preparation, Kubernetes, Technical Documentation, Collaboration, Documentation, Design, Containerization, Docker, Azure

Industry

Information Technology/IT

Description

KEY QUALIFICATIONS

  • 2-5 Years Experience
  • MLOps and CI/CD Expertise: Proven experience in designing and implementing CI/CD pipelines for machine learning models, including containerization and deployment using tools such as Docker, Kubernetes, and Terraform. Hands-on knowledge of MLOps platforms such as MLflow for experiment tracking and model management, along with workflow orchestration tools like Apache Airflow, Kubeflow, or equivalent. Strong background in monitoring and maintaining production models, including performance tracking, drift detection, and automated retraining strategies.
  • Cloud Infrastructure: Practical experience building and managing secure, scalable machine learning environments on cloud platforms such as AWS, GCP, or Azure.
  • Machine Learning Fundamentals: Proficiency in model evaluation using standard metrics including AUC, recall, precision, and F1-score. Solid understanding of the full machine learning lifecycle—from data preparation and model training to validation, deployment, and pipeline optimization.
  • Communication & Collaboration: Works closely with a Platform Architect and a PM. Must clearly communicate technical concepts and collaborate on design for modularity and scalability.
  • Documentation & Knowledge Transfer: A key deliverable is handover to an internal team. Must create clear, comprehensive technical documentation and be adept at teaching/enabling others to ensure project sustainability.
Responsibilities
  • Establish secure, cloud-based machine learning development environments (AWS, GCP, or Azure).
  • Construct automated pipelines for data preparation, training, and model validation (e.g., MLflow, Airflow).
  • Implement CI/CD workflows for deploying models to staging and production environments (e.g., Docker, Kubernetes, Terraform).
  • Develop and integrate monitoring and retraining triggers based on model drift, performance degradation, or newly acquired data.
  • Conduct evaluations comparing baseline and experimental models using metrics such as AUC, recall, precision, and F1-score.
  • Collaborate with the Architect to ensure the modularity and extensibility of pipeline design.
  • Provide internal team enablement through knowledge transfer and comprehensive technical documentation.
Loading...