Closed listing
Machine Learning Engineer
- Toronto, ON, Canada
$60 to $70 CAD / hour · Contract
This opening has closed.
The original listing is kept below for reference.
Job details
- Pay
- $60 to $70 CAD / hour
- Job type
- Contract
- Closing date
- Experience
- 3+ years of ML Engineering, Data Engineering, or Software Engineering experience
- Posting language
- English
- Posted
Similar jobs hiring now
Search current openingsOriginal job description
Archived listing. The details below describe a past opening.
Day-to-Day
Insight Global is looking for a Machine Learning Engineer to put into production forecasting models and build the monitoring, observability, and explain capabilities needed for trusted business forecasting.
The role partners closely with data scientists, demand planners, and platform teams to deliver scalable and reliable forecasting solutions.
Key Responsibilities
- Refactor forecasting models into production-ready, tested, and reusable components
- Establish engineering best practices, standards, and development workflows
- Design and maintain training, backtesting, and inference pipelines in Azure ML
- Develop feature engineering and data preparation solutions in Snowflake
- Automate deployment, testing, model promotion, and rollback processes using Azure DevOps
- Support forecast integration with the o9 planning platform
- Build monitoring for data quality, drift detection, pipeline health, and forecast accuracy
- Implement model lineage, traceability, and governance capabilities
- Develop explainability solutions and forecasting insights for business users
- Create technical documentation and communicate solutions to both technical and business stakeholders
Required Skills & Experience
- 3+ years of ML Engineering, Data Engineering, or Software Engineering experience
- Strong Python development and software engineering fundamentals
- Production experience with Azure ML (pipelines, compute, model registry, endpoints, MLflow)
- Strong SQL and Snowflake expertise
- CI/CD experience using Azure DevOps or similar tools
- Experience building ML monitoring and observability frameworks
- Knowledge of explainability techniques (SHAP, permutation importance, forecast decomposition)
- Time series forecasting experience, including backtesting and evaluation
- Strong communication and stakeholder management skills
Nice to Have Skills & Experience
- Experience with o9 Solutions, SAP IBP, Kinaxis, or Blue Yonder
- CPG, retail, or supply chain planning experience
- Databricks, Spark, dbt, Azure Data Factory, Power BI
- Feature stores, containerisation, and Infrastructure as Code (IaC)
Vacancy: This posting is for a currently vacant role, and the successful candidate will be hired into an existing open position.
Pay Rate: $60-70/hr
We may use artificial intelligence tools to assist with the screening, assessment, or selection of potential applicants for this position.
More about this job
Responsibilities
The role focuses on putting forecasting models into production and building the necessary monitoring, observability, and explainability capabilities. It involves designing training and inference pipelines in Azure ML and integrating forecasts with the o9 planning platform.
Requirements
Candidates need over 3 years of experience in ML, Data, or Software Engineering with strong proficiency in Python, SQL, and Snowflake. Production experience with Azure ML and CI/CD tools like Azure DevOps is required.
Skills
- Python
- Azure ML
- SQL
- Snowflake
- Azure DevOps
- CI/CD
- ML Monitoring
- SHAP
- Time Series Forecasting
- Software Engineering
- Data Engineering
- Model Governance
- Feature Engineering
- MLflow
- Stakeholder Management
- Technical Documentation
Visa sponsorship
Not detected in the job text
Categories
- Data & Analytics
- Technology
- Software
- Engineering
- Consulting
Keywords
- Machine Learning
- Azure ML
- Snowflake
- Azure DevOps
- Python
- SQL
- CI/CD
- MLflow
- SHAP
- Time Series Forecasting
- o9 Solutions
- SAP IBP
- Kinaxis
- Blue Yonder
- Databricks
- Spark
- dbt
- Azure Data Factory
- Power BI
- Infrastructure as Code
- Containerisation
- Feature Stores
- Model Lineage
- Drift Detection
- Backtesting
- Supply Chain Planning
- CPG
- Retail
- Observability
- Explainability