Productionize the science Refactor experimental forecasting code into modular, tested, reproducible components with clear interfaces and versioned configuration.
Establish the patterns others follow: repo structure, testing strategy, code review standards, dependency and environment management. Build and enhance ML pipelines Design, build, and harden training, backtesting, and inference pipelines in Azure ML. Build feature engineering and data preparation on Snowflake, with attention to cost, query performance, and data contracts with upstream sources.
Automate build, test, and deployment through Azure DevOps, including model promotion and rollback paths. Support the forecast handoff into o9 so outputs land reliably on the planning cadence. ML observability Instrument pipelines for data quality, schema and feature drift, training/serving skew, and pipeline health.
Build forecast accuracy monitoring that reflects how the business actually measures it — accuracy and bias sliced by category, customer, and horizon — with alerting and clear ownership for what fires.
Make model lineage traceable: which data, which code, which config produced which forecast. Deliver driver-level explanations of forecast movements that a demand planner can read without a data science background. Implement feature attribution and forecast decomposition, and surface it in artifacts and dashboards that reach the people making planning decisions.
Communication
Write short, clear design docs and decision records before building. Present tradeoffs and results to technical and business stakeholders, and translate planner feedback into engineering work. 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. Solid 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. Clear written and verbal communication with non-technical stakeholders. Direct experience with o9 Solutions, or comparable planning platforms (SAP IBP, Kinaxis, Blue Yonder).
CPG, retail, or consumer goods demand planning and supply chain context. Databricks/Spark, dbt, Azure Data Factory, Power BI. Qualified candidates will receive consideration for employment regardless of their race, color, ethnicity, religion, sex (including pregnancy), sexual orientation, gender identity and expression, marital status, national origin, ancestry, genetic factors, age, disability, protected veteran status, military or uniformed service member status, or any other status or characteristic protected by applicable laws, regulations, and ordinances.
If you need assistance and/or a reasonable accommodation due to a disability during the application or recruiting process, please send a request to
[email protected] learn more about how we collect, keep, and process your private information, please review Insight Global's Workforce Privacy Policy: Refactor experimental forecasting code into modular, tested, reproducible components with clear interfaces and versioned configuration.
Establish the patterns others follow: repo structure, testing strategy, code review standards, dependency and environment management. Build and enhance ML pipelines Design, build, and harden training, backtesting, and inference pipelines in Azure ML. Build feature engineering and data preparation on Snowflake, with attention to cost, query performance, and data contracts with upstream sources.
Automate build, test,
and deployment through Azure DevOps, including model promotion and rollback paths. Support the forecast handoff into o9 so outputs land reliably on the planning cadence. ML observability Instrument pipelines for data quality, schema and feature drift, training/serving skew, and pipeline health.
Build forecast accuracy monitoring that reflects how the business actually measures it — accuracy and bias sliced by category, customer, and horizon — with alerting and clear ownership for what fires.
Make model lineage traceable: which data, which code, which config produced which forecast. Deliver driver-level explanations of forecast movements that a demand planner can read without a data science background. Implement feature attribution and forecast decomposition, and surface it in artifacts and dashboards that reach the people making planning decisions.
Write short, clear design docs and decision records before building. Present tradeoffs and results to technical and business stakeholders, and translate planner feedback into engineering work. 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. Clear written and verbal communication with non-technical stakeholders. Direct experience with o9 Solutions, or comparable planning platforms (SAP IBP, Kinaxis, Blue Yonder).
CPG, retail, or consumer goods demand planning and supply chain context. Databricks/Spark, dbt, Azure Data Factory, Power BI.
📌 Medical Engineer (Toronto)
🏢 Insight Global
📍 Toronto