Senior ML/AI Engineer

Sportchek; Toronto; Hybrid; CAD 64,000 - 90,000; Full time

Benefits offered by this job

Comprehensive benefits

Career growth opportunities

Product discounts

Job summary

Sportchek in Toronto, ON, seeks a Senior ML/AI Engineer to own end-to-end ML initiatives from data to deployment. You will design offline evaluation, implement ranking models, and build scalable feature pipelines over massive transaction data.

You will work with PyTorch/TensorFlow, Spark, and cloud ML platforms to deliver production-grade models, while mentoring teammates and improving the engineering standards of the team.

Qualifications

• 3+ years of production ML experience with end-to-end ownership.
• Experience in retail, loyalty, personalization, or ad-tech ranking preferred.
• Expert-level Python and production-grade ML code.
• Strong SQL and PySpark data processing capabilities.
• Experience with recommender systems or large-scale ranking.

Responsibilities

• Develop deep understanding of retail business, loyalty programs, and personalized offers.
• Design offline evaluation frameworks with explicit success criteria.
• Build and optimize large-scale feature engineering in PySpark.
• Design and operate ML platform layers and training pipelines.
• Lead multi-source analytical pipelines and mentor adjacent engineers.

Skills

Python

SQL

Spark / PySpark

Recommender systems

Offline evaluation

Education

Bachelor's degree

Master's degree

PhD

Tools

PyTorch

TensorFlow

LightGBM

XGBoost

Vertex AI

SageMaker

Azure ML

BigQuery

Airflow

Terraform

Job description

## Senior ML/AI EngineerApply: Toronto, ON: Full time: Posted 8 Days Ago: End Date: September 22, 2026 (5 days left to apply): JR164829**What You'll Do:*** Develop a deep understanding of our Retail business, Loyalty program, and how personalized offers are composed and delivered across our retail banners.* Design and deliver offline evaluation frameworks with explicit success criteria — ranking metrics, held-out AUC, time-respecting splits, and point-in-time correctness — so that an offline win reliably predicts online lift.* Research and apply modelling methodology to select (and justify) the right approach for a given business problem, from matrix factorization and two-tower retrieval to learning-to-rank and sequential architectures.* Build and optimize large-scale feature engineering in PySpark over hundreds of millions of transaction records, with the profiling skills to know why a job is shuffling.* Design and operate our ML platform layer — feature store, reproducible training pipelines, and cloud training job submission — so retraining is cheap and routine rather than a project.* Design and implement agentic AI solutions that automate model improvement — extending our in-house harness where an AI agent proposes changes, scores them against a locked benchmark, and keeps only what measurably helps, under human review.* Lead optimization and orchestration of end-to-end analytical pipelines across multiple data sources and modelling workstreams to ensure scalability and production reliability.* Raise the engineering standard of the team through code review, documentation, and mentorship of engineers working adjacent to the model layer.**What You Bring:*** B.S or M.S, preferably in Computer Science/Statistics/Math/Engineering or a related quantitative discipline. PhD an asset.* 3+ years experience developing and deploying machine learning solutions in production — owning data, training, evaluation, release, and operational support. Experience in retail, loyalty programs, personalization, or ad-tech ranking preferred.* Expert-level Python, writing production-grade ML code rather than notebooks handed off for deployment.* 4+ years of experience querying and analyzing large datasets with tools such as SQL and Spark, with demonstrated depth in PySpark.* Demonstrated experience with recommender systems or large-scale ranking, and the judgment to know which technique a problem actually requires.* Rigorous approach to offline evaluation — including train/validation splits that respect time, point-in-time correct feature construction, and leakage you have personally found and fixed.* Experience with deep learning frameworks (PyTorch, TensorFlow) and gradient boosting libraries such as LightGBM or XGBoost.* Production experience with a major cloud ML platform — Vertex AI preferred; SageMaker or Azure ML acceptable — including custom training jobs, artifact management, and cost control. Familiarity with BigQuery and cloud-based data structures is an asset.* Experience designing and orchestrating multi-stage analytical pipelines with workflow optimization, preferably Apache Airflow at production scale.* Familiarity with agentic AI architectures, LLM-based solutions, and working fluently with coding agents is a strong asset. Infrastructure-as-code experience (Terraform) and cloud IAM familiarity is an asset.* Excellent oral and written communication skills, with the ability to communicate both technical and business concepts, as well as strong presentation skills.* Demonstrated ability to work independently with minimal supervision, effectively navigating and resolving ambiguous problems and situations.**Location**: Toronto, Ontario (Hybrid: In-office 4 days a week)We’re always looking for great talent! In addition to competitive pay, we offer:* Comprehensive benefits and retirement programs* Performance incentives, Continuing Education Programs* Other perks to support your well-being* Career growth opportunities and product discounts**Broadband Salary Range:** $64,000 – $106,000. Our typical *hiring range* is between $64,000 and $85,000. Salary decisions are also dependent on other factors such as your experience, industry benchmarks, internal equity and other role-specific requirements. For critical roles, the compensation offering will be reviewed to ensure alignment with market rate and conditions and the unique value you bring to the role.