Senior Machine Learning Engineer, Causal & Decision Systems

CSC Generation•Toronto, ON

About The Position

CSC Generation is building closed-loop decision systems that use machine learning to operate consumer businesses more intelligently. We are starting with pricing and expanding into areas such as inventory, purchasing, promotions, marketing, and assortment. You will help build systems that estimate causal response, quantify uncertainty, choose actions, generate useful information, observe outcomes, update policies, evaluate challengers, and deploy within guardrails. We want to answer questions such as: What happens because we change a price, rather than simply what happens next? How should uncertainty affect a decision? When should the system exploit what it knows versus experiment to learn? Can we estimate the value of a challenger policy before fully deploying it? How do we optimize economic outcomes while respecting inventory, margin, vendor, customer, and operational constraints?

Requirements

Strong technical ability and judgment
Experience in machine learning and statistical modeling
Experience in causal inference and experimentation
Experience in recommendation, advertising, pricing, marketplace, credit, or other decision systems
Experience with bandits, reinforcement learning, optimization, or active learning
Experience with uncertainty estimation
Experience with counterfactual evaluation
Experience with production ML systems
Proficiency in Python
Proficiency in SQL
Experience with large behavioral datasets

Nice To Haves

Experience in causal and heterogeneous treatment-effect modeling
Experience in uncertainty estimation and calibration
Experience in contextual bandits, active learning, or sequential decision-making
Experience in policy learning and constrained optimization
Experience in counterfactual and off-policy evaluation
Experience in experimentation and champion/challenger systems
Experience in production ML infrastructure, monitoring, and automated deployment

Responsibilities

Estimate causal response and quantify uncertainty
Choose actions based on learned policies
Generate useful information from system operations
Observe outcomes and update policies
Evaluate challenger policies before full deployment
Optimize economic outcomes while respecting constraints
Build systems that learn from their own interventions
Safely automate an increasing share of real commercial decisions
Apply causal inference and experimentation techniques
Develop contextual bandits, active learning, or sequential decision-making algorithms
Implement policy learning and constrained optimization
Perform counterfactual and off-policy evaluation
Develop experimentation and champion/challenger systems
Work with production ML infrastructure, monitoring, and automated deployment