Senior Data Scientist role within our client's Advanced Analytics team. This posting is for two headcount and both are end-to-end data science roles and are interchangeable by design. Role Summary:

The Advanced Analytics team is building a trusted, machine-learning-driven capacity-planning capability in-house. The Senior Data Scientist designs, builds, and validates predictive and decision-support models for airport operations. Each person takes a problem from raw operational data through validated models to outputs that operational and business stakeholders can trust and act on. Two scientists are being hired to provide the team with depth, resilience, and the capacity to scale across workstreams. This is a hands-on ownership role. The priority is turning complex, imperfect operational data into accurate, explainable, and supportable analytics. Accuracy and explainability are the standard, not optional extras. Details:

Scope of Ownership:

Senior Data Scientist owns analytical workstreams end to end. The following areas describe the scope of ownership for each role. Data foundation

Validate and prepare operational data; establish trusted, analytics-ready datasets. Build demand forecasts and predictive models using statistical, time-series, and machine learning methods. Translate predictions into capacity, risk, and recommendation outputs that inform operational decisions. Validation

Define and run validation that reflects real operational conditions, not only average-case accuracy. Production readiness

Package models for deployment and monitoring in partnership with ML engineering. Stakeholder Trust

Communicate methods, assumptions, and limitations clearly to technical and non-technical audiences. Each role spans the full analytics lifecycle.



The successful candidate is comfortable across the following areas:Data discovery and validation — profiling, quality checks, and source reconciliation. Modelling — statistical, time-series, and machine learning approaches, with robust baselines before advanced methods. Optimization and decision support — converting model outputs into actionable, constraint-aware recommendations. Productionization — collaborating with MLOps and ML engineering to deploy, monitor, and maintain models. Business consumption — partnering with business intelligence and operational stakeholders to make outputs usable and trusted. Key Responsibilities:

The Senior Data Scientist is expected to perform the following responsibilities:Own analytical workstreams end to end, from data to validated, decision-ready outputs. Validate operational data and define clear, defensible data foundations before modelling. Build transparent baselines before advanced models and justify any added complexity. Apply statistical, time-series, machine learning, and optimization methods as appropriate. Validate models against real operational conditions and communicate performance honestly. Translate model outputs into recommendations stakeholders can act on with confidence. Partner with Data Engineering, Business Intelligence, Operations, and MLOps / ML engineering. Produce production-readiness artifacts and support clean handoff to deployment and monitoring.



Communicate uncertainty and limits clearly, and identify when an output is not ready for operational use. Required Experience:

Candidates are required to demonstrate the following experience: Five or more years in data science, forecasting, operations analytics, or applied machine learning. Strong Python and SQL. Time-series, regression, gradient boosting, or statistical modelling experience. Demonstrated ability to work from messy operational data to trusted, validated outputs. Ability to explain model performance and limitations to technical and business stakeholders. Evidence of owning work through to handoff or production, not only exploratory analysis. Preferred Experience:

The following experience is considered an asset:Airport, airline, transit, logistics, or other complex operations experience. Forecasting, queueing, simulation, or optimization methods. Microsoft Fabric, Power BI, Azure Machine Learning (Azure ML), MLflow, and Git. Model governance: versioning, validation, monitoring, and retraining practices. Experience designing decision-support or recommendation outputs. Success Measures:

Performance in the role is measured against the following outcomes: Models are accurate, explainable, and trusted by operational and business stakeholders. Performance is validated against real operational conditions, not only average accuracy. Outputs are reconciled, supportable, and ready for production handoff. Work is handed to ML engineering with complete artifacts and minimal rework. The two scientists provide mutual coverage and a consistent quality bar across workstreams. Why Join Us?

You'll have the opportunity to shape products that bring analytics and

📌 Sr. Data Scientist (Mississauga)
🏢 Tundra Technical Solutions
📍 Mississauga