Ground every answer in facts on this page and the original listing. We never invent Glassdoor-style reviews or salaries that are not in our data.
Expect deep dives on causal identification, confounding, uplift/policy learning, and how you validate decision systems under distribution shift. Prepare examples of productionizing ML for product decisions, collaborating with non-ML stakeholders, and trading off model complexity vs. operational reliability in multi-brand retail settings.
Strong fit if you enjoy senior causal/decision ML in a portfolio retail platform (e.g., home brands, outdoor retail M&A context) and hybrid work in Toronto. Thin public employer-review data; weight the role scope and your causal production experience more than brand recognition.
As a Senior Machine Learning Engineer focused on causal and decision systems at CSC Generation, a typical day centers on framing retail and brand decisions as causal problems: identifying treatments and outcomes, building or reviewing uplift and policy models, and stress-testing assumptions with product and data partners. You would ship evaluation code, monitor offline vs online decision quality, and partner with engineering so recommendations stay safe, measurable, and production-ready for multi-brand commerce operations.
Prioritize causal inference and decision policy evaluation, experiment design, and production ML (feature pipelines, monitoring, offline/online parity). Strengthen Python, probabilistic modeling, and clear stakeholder communication for brand/ops partners. No certification list or costs are provided in the source data.
Public profiles and trade press describe a tech platform behind home and retail brands, including coverage of acquiring Backcountry and building a large home-brand portfolio.
The listing marks remote as off and location as hybrid Toronto, ON—so expect in-office days in Toronto unless the employer states otherwise later.
No verified salary bands, Glassdoor/Indeed ratings, or employee review scores were supplied in the data, so none are stated.
Public-domain labor data — prepare examples for 2–3 of these.
Website: contactout.com
Public cache only — not an employee review.
Senior Machine Learning Engineer, Causal & Decision Systems at Cscgeneration-2 in Toronto, ON (Hybrid) What This Role Involves The role involves building systems that estimate causal responses and quantify uncertainty, choosing actions based on these estimates, generating useful information, observing outcomes, updating policies, evaluating challengers, and deploying within guardrails. Key questions include: What happens because we change a price? How should uncertainty affect a decision? When to exploit knowledge versus experiment for learning? Can the value of a challenger policy be estimated before full deployment? How can economic outcomes be optimized while respecting constraints? What You'll Do You will work on various projects depending on your background, including causal and heterogeneous treatment-effect modeling; uncertainty estimation and calibration; contextual bandits, active learning, or sequential decision-making; policy learning and constrained optimization; counterfactual and off-policy evaluation; experimentation and champion/challenger systems; production ML infrastructure, monitoring, and automated deployment. The focus is on selecting the right method rather than using a specific framework. Who We're Looking For We are seeking candidates with strong skills in causal inference, machine learning, and decision-making under uncertainty. Experience in modeling complex systems, handling large datasets, and developing robust ML infrastructure is essential. A deep understanding of economic principles and business operations is also required. About the Company CSC Generation builds closed-loop decision systems that use machine learning to operate consumer businesses more intelligently. Starting with pricing, we are expanding into inventory, purchasing, promotions, marketing, and assortment. Our goal is to create systems that produce measurable economic lift in controlled experiments, generalize across businesses, learn from interventions, and safely automate increasing commercial decisions. Apply Today To apply, complete your application directly on this page, or you'll be redirected to the employer's application platform to finish submitting there.
Generated for personal interview prep · 2026-08-15 UTC · getajob.ai