Lead technical strategy and hands-on development of large-scale optimization and ML systems (routing, scheduling, resource allocation). Design MILP/VRP/constraint solutions, integrate forecasting with optimization, deploy on cloud/lakehouse, mentor a data science team, and partner with stakeholders to deliver measurable operational improvements.
About the Role
We are hiring a Lead Data Scientist to own the technical strategy and hands-on development of large-scale optimization and machine learning systems that drive real operational decisions — routing, scheduling, resource allocation, network design, or forecasting-driven planning. You will lead the design of Mixed-Integer Linear Programming (MILP), Vehicle Routing Problem (VRP), constraint programming, and machine learning solutions that turn complex, high-volume operational problems into scalable, production decision systems.
This is a player-coach position. You will set technical direction and mentor a team of data scientists while staying hands-on in solver design, model architecture, and production deployment. You will partner directly with business, engineering, and executive stakeholders to turn operational challenges into optimization systems that deliver measurable gains in cost, efficiency, and service quality — skills that translate directly across supply chain, logistics, workforce, network, and resource-planning problems.
What You'll Do
Optimization & Model Architecture
- Own the technical architecture of large-scale optimization systems built on MILP/MIP, constraint programming, and heuristic/metaheuristic solvers (e.g., Gurobi, CPLEX, OR-Tools).
- Design and scale routing, scheduling, resource allocation, and network optimization models that account for real-world constraints such as capacity, time windows, territory or zoning restrictions, and service-level commitments.
- Set modeling standards, solver performance benchmarks, and reusable optimization frameworks used across the data science team.
- Integrate ML-based forecasting (demand, consumption, ETAs, anomalies) with the optimization engine to move decision-making from reactive to prescriptive.
Technical Leadership & Delivery
- Define the architecture for deploying optimization and ML solutions in production on cloud/lakehouse platforms (e.g., Azure, Databricks), including validation, monitoring, and rollback strategy.
- Lead design reviews and set the bar for model governance, testing, and code quality across the team.
- Partner with Data Engineering to productionize solvers and pipelines at the throughput required for large-scale, recurring optimization runs.
- Stakeholder Partnership & Team Leadership
- Translate operational priorities from business and operations leaders into a prioritized optimization roadmap.
- Present model trade-offs, assumptions, and business impact clearly to executive and non-technical audiences.
- Hire, mentor, and grow a team of data scientists and optimization engineers; establish career development, code review, and model review practices.
Required Qualifications
- 10+ years of experience in Data Science, Operations Research, Applied Mathematics, Industrial Engineering, or an equivalent quantitative field, including 3+ years leading or mentoring a team.
- A proven track record shipping production MILP/MIP or VRP systems that solve real routing, scheduling, resource allocation, or network optimization problems at scale — not only academic or proof-of-concept work.
- Expert-level Python and SQL, with hands-on experience using at least one commercial-grade solver (Gurobi, CPLEX) and/or OR-Tools.
- Experience combining ML forecasting with optimization (e.g., demand or consumption forecasting feeding a scheduling or planning engine).
- Experience deploying and operating models on cloud/lakehouse platforms (Azure, Databricks, or equivalent).
- Strong written and verbal communication; comfortable presenting technical trade-offs to executive stakeholders.
Preferred Qualifications
- Master's or PhD in Operations Research, Applied Mathematics, Industrial Engineering, Data Science, or a related field.
- Experience applying optimization in supply chain, logistics, transportation, manufacturing, retail, or field-operations settings.
- Familiarity with simulation, digital twins, reinforcement learning, or prescriptive analytics.
- Experience with Spark or distributed computing for large-scale data processing.
- Exposure to MLOps and model governance frameworks.
Tools & Technologies
Python •SQL • Gurobi / CPLEX / OR-Tools • Azure • Databricks •MILP / VRP • Spark • MLOps
Why TechBlocks
- Work directly with Fortune 500 executives and digital transformation leaders.
- Be part of a fast-growing, AI-native software engineering firm redefining global delivery through our GCC-as-a-Service model.
- Collaborate with global teams in Canada, the U.S., and India on cutting-edge cloud and AI initiatives.
- Competitive compensation, performance incentives, and a culture that values ownership, agility, and innovation.
TechBlocks Vaughan, Ontario, CAN Office
Suite 4,, 399 Applewood Crescent, , , Vaughan, Ontario , Canada, L4K 4J3
Similar Jobs
Information Technology
Build and maintain predictive models, including propensity-to-upgrade and engagement scoring, to drive AI product adoption and customer expansion. Develop features from product, behavioral, campaign, learning, and firmographic data. Partner with Marketing, Customer Success, Data Engineering, Product, and Commercial teams to operationalize models in Treasure Data and activation workflows. Monitor model performance, support experimentation, measure lift, document methodologies, and communicate insights to technical and nontechnical stakeholders.
Top Skills:
Customer Data PlatformPythonTreasure Data
Blockchain • Fintech • Payments • Consulting • Cryptocurrency • Cybersecurity • Quantum Computing
Lead development, deployment, and monitoring of end-to-end ML/DL/AI solutions. Responsibilities include data extraction, cleaning, modeling, evaluation, production deployment, documentation, and presenting results. Collaborate across teams, build prototypes and POCs, protect IP, and disseminate knowledge externally.
Top Skills:
AzureAzure Machine LearningDatabricksHadoopLinuxPythonPyTorchRSap HanaScikit-LearnSnowflakeSQLTensorFlow
Healthtech
Leads the design, development, deployment, and scaling of AI, machine learning, generative AI, and agentic AI solutions for commercial pharmaceutical operations. Owns the full AI product lifecycle, advises on architecture and modeling, partners with cross-functional stakeholders, ensures responsible AI governance, develops reusable frameworks, communicates insights, mentors technical staff, and supports organizational AI strategy and capability building.
Top Skills:
AngularSparkAWSConfluenceFuzzy String MatchingGCPGoJavaJIRALangchainLanggraphAzureNlpNode.jsNoSQLPythonRegexRest ApisSnowflakeSQLTransformersTypescriptVector Databases
What you need to know about the Toronto Tech Scene
Although home to some of the biggest names in tech, including Google, Microsoft and Amazon, Toronto has established itself as one of the largest startup ecosystems in the world. And with over 2,000 startups — more than 30 percent of the country's total startups — Toronto continues to attract new businesses. Be it helping entrepreneurs manage their finances, simplifying business operations by automating payroll or assisting pharmaceutical companies in launching new drugs, the city's tech scene is just getting started.
