Senior ML Engineer — Production Forecasting Pipelines

Insight Global; Toronto; On-site; CAD 140,000 - 210,000; Full time

Job summary

Insight Global is seeking an ML engineering leader to productionize forecasting science, refactor code into modular components, and establish robust patterns for testing and deployment in Azure ML and Azure DevOps. You will design end-to-end ML pipelines, build feature engineering on Snowflake, optimize for cost and performance, and ensure reliable handoffs to planning systems like o9.

The role emphasizes observability, explainability, and clear communication with stakeholders, with ownership of

Qualifications

• 8+ years in ML engineering, data engineering, or software engineering, with substantial recent time at a staff/lead level of technical scope.
• Strong Python and software engineering fundamentals — testing, packaging, code review, refactoring legacy or exploratory code without breaking behavior.
• Production experience with Azure ML: jobs, pipelines, compute, model registry, endpoints, MLflow tracking.
• Strong SQL and Snowflake experience, including performance and cost tuning on large tables.
• CI/CD experience with Azure DevOps (or equivalent) for ML workloads.
• Demonstrated experience building ML monitoring and observability in production — not just standing up a dashboard, but defining what to measure and what to do when it moves.
• Working knowledge of explainability methods (e.g. SHAP, permutation importance, forecast decomposition) and the judgment to know their limits.
• Time series forecasting experience: hierarchical forecasts, intermittent demand, proper backtesting and evaluation design.
• Clear written and verbal communication with non-technical stakeholders.

Responsibilities

• Productionize the science by refactoring forecasting code into modular, tested components.
• Establish repo structure, testing strategy, code review standards, and environment management.
• Design and build ML pipelines for training, backtesting, and inference in Azure ML.
• Develop feature engineering and data prep on Snowflake with cost and performance focus.
• Automate build, test, and deployment through Azure DevOps, including model promotion and rollback.
• Handoff forecast into o9 planning cadence ensuring reliable outputs.
• Instrument pipelines for data quality, drift, and pipeline health for ML observability.
• Build forecast accuracy monitoring with metrics and alerting for business relevance.
• Trace model lineage to data, code, and config.
• Provide driver-level explanations of forecasts for non-data-science stakeholders.
• Surface feature attribution and forecast decomposition in dashboards for planners.
• Create concise design docs and present tradeoffs to stakeholders; incorporate feedback.
• Ensure the codebase and docs can be owned by the internal team after engagement ends.

Skills

Python

Software engineering

Azure ML

ML monitoring

Time series forecasting

SQL

Snowflake

CI/CD

Azure DevOps

Explainability methods

Communication

Tools

MLflow

Azure DevOps

Snowflake

Databricks

Power BI

Job description

Insight Global is seeking an ML engineering leader to productionize forecasting science, refactor code into modular components, and establish robust patterns for testing and deployment in Azure ML and Azure DevOps. You will design end-to-end ML pipelines, build feature engineering on Snowflake, optimize for cost and performance, and ensure reliable handoffs to planning systems like o9.

The role emphasizes observability, explainability, and clear communication with stakeholders, with ownership of