ABOUT STOREFORCE
StoreForce is deeply passionate about Retail – it’s in our roots and part of every single line of code we write. We’re known to say we’re Retailers first, and a technology vendor second. Every day we strive to help Retailers set a new standard for operational excellence, changing the way retailers think, manage and perform.
Now is a great time to be joining us as you can make a real impact in helping us accelerate our growth while working with some of the world’s best known retail brands. We thrive on change, collaboration, and trust and invest in, as well as support our people, celebrating diversity and fostering a space for them to learn and grow every day.
From day one, you’ll get a warm welcome as well as the tools and information you need to perform at your best with regular one-to-ones and personal development planning for growth. You’ll also have practical opportunities to learn from other experts and attend in person events to quickly feel integral to a growing and diverse global team.
OVERVIEW
Reporting to the VP, Technical Operations, the Senior Data Scientist is a senior, hands-on individual contributor on our Engineering, Data Platform team. This is a full-time, remote role open to candidates based in the United States or Canada, with no direct reports.
StoreForce helps specialty retailers run their stores, from workforce scheduling to performance analytics, across tens of thousands of locations worldwide. We are building a data platform on Azure Databricks that brings years of sales, traffic, labor, and store execution data from every customer into one governed lakehouse.
As a Senior Data Scientist, you will turn that data into forecasts, benchmarks, and recommendations that appear inside our products. This is a full-stack role: you will write the Spark and SQL transformations that shape raw data into trusted tables and features, build and validate the models, and run them in production. You will work in a small platform team with product, engineering, and customer-facing colleagues.
RESPONSIBILITIES
1. Data Transformation & Feature Engineering
- Own the transformation layer: Spark and SQL transformations that turn raw data already in the lakehouse into silver and gold tables.
- Build and maintain the dimensional model shared across both product lines, along with the tests and reconciliation that keep those tables correct.
- Build reusable, point-in-time correct feature tables over the full cross-tenant history.
- Map each customer’s configurable metrics to one governed schema.
2. Semantic Layer & Retail KPIs
- Implement StoreForce’s retail KPI logic in the governed semantic layer (Unity Catalog Metric Views), including fiscal calendars, 53-week comparisons, comp days, and targets.
- Ensure dashboards, applications, models, and AI agents all use the same certified numbers.
3. Forecasting & Insight Products
- Develop, backtest, and ship forecasting models for traffic, sales, and labor demand at store, day, and intraday grain.
- Start from simple baselines and add complexity only where accuracy improves.
- Deliver the wider set of insight products: store clustering, anomaly detection, and conversion and labor driver analysis.
- Build cross-customer benchmarking and analysis that links store execution (tasks, audits, training) to sales results.
4. Production Machine Learning
- Manage experiment tracking and the model registry in MLflow and Unity Catalog.
- Run scheduled batch scoring that writes predictions back to gold tables.
- Monitor models for accuracy, drift, and cost, and retrain when the numbers call for it.
5. Customer Data Protection & AI Analytics
- Protect customer data in everything you build: models and benchmarks that train across customers expose aggregate signal only.
- Ensure every output respects per-tenant row and column security.
- Improve the natural-language analytics experience (Databricks Genie and LLM-based agents) by curating the semantic layer, building evaluation sets, and measuring answer quality.
6. Collaboration & Communication
- Frame problems with product and customer teams.
- Design tests that measure whether a model changed an outcome.
- Explain results and limits to non-technical audiences.
Other duties as assigned by your manager and senior leadership.
QUALIFICATIONS
Competencies Required:
- Analytical Rigor - Applies sound statistics and says clearly when the data cannot support a conclusion
- Full-Stack Ownership - Owns the work end to end, from raw data and transformations to models running in production
- Pragmatism - Starts with simple baselines and adds complexity only where it improves results
- Customer & Product Focus - Frames problems around product and customer outcomes and measures real impact
- Data Stewardship - Protects customer data and treats data correctness as non-negotiable
- Communication - Explains results and limits clearly to engineers, product managers, and non-technical audiences
EXPERIENCE / KNOWLEDGE
- 5+ years in data science or machine learning, with models you built running in production and used by a product or by customers
- Strong Python for data and modeling work (pandas or Polars, scikit-learn, gradient boosting such as LightGBM or XGBoost) and strong SQL (window functions, complex joins, query optimization)
- Depth in time series forecasting: seasonality, holidays and calendar effects, backtesting, and choosing error metrics that match the business decision
- Hands-on transformation work: you have built and maintained the tested, version-controlled tables your models train on, in SQL and Spark or a similar engine (dbt, Snowflake, BigQuery)
- Production machine learning practice: experiment tracking, a model registry, scheduled scoring, monitoring, and retraining, using MLflow or an equivalent
- Sound statistics: experimental design, uncertainty, and the judgment to say when the data cannot support a conclusion
- Clear written and spoken communication with engineers, product managers, and customers.
If you meet most of these qualifications and are strong in forecasting and SQL, we encourage you to apply.
PREFERRED QUALIFICATIONS
- Production experience on Databricks:
Unity Catalog, Lakeflow Spark Declarative Pipelines and Lakeflow Jobs, MLflow, Feature Store, Model Serving, and Metric Views - Experience with hierarchical and intermittent forecasting, and with dimensional modeling, incremental processing, and CI/CD for data transformations
- Experience in retail, workforce management, labor scheduling, or store operations analytics
- Experience with multi-tenant SaaS data, including modeling across customers while keeping each customer’s data isolated
- Experience with optimization methods (for example, labor coverage or schedule optimization) or causal inference
- Experience building with LLM providers (Anthropic Claude and OpenAI) and evaluating LLM applications over structured data: Genie, agent frameworks, evaluation sets, and guardrails
- A graduate degree in statistics, computer science, operations research, or another quantitative field, or equivalent experience.
TECHNICAL ENVIRONMENT
You don’t need experience with every technology named here.
- Platform - Azure Databricks; the platform team brings data from our multi-tenant SQL Server estate into the lakehouse, and your work starts there
- Transformation - PySpark, Spark SQL, and Lakeflow Spark Declarative Pipelines
- Storage - Delta Lake on Azure Data Lake Storage Gen2
- Governance - Unity Catalog for governance, features, models, and Metric Views
- Training & Scoring - MLflow and Lakeflow Jobs for training and batch scoring; Model Serving where a real-time endpoint is needed
- Serving - Databricks SQL and Lakebase for serving results
- AI Analytics - Genie with Claude or OpenAI models for natural-language analytics
- Delivery - Everything as code through Declarative Automation Bundles and CI/CD
KEY PERFORMANCE INDICATORS (KPIs)
- Forecast accuracy for traffic, sales, and labor demand models against baselines and agreed targets, in backtesting and in production
- Reconciliation of governed KPIs to the existing application’s numbers, and test pass rates on silver and gold tables
- Number of models and insight products shipped into production and adopted by customers
- Measured impact of models on customer outcomes, validated through designed tests
- Model health in production: scoring job success, drift detection, retraining cadence, and compute cost
- Zero cross-tenant data exposure across models, benchmarks, and outputs
- Natural-language analytics answer quality measured against evaluation sets
- Satisfaction of product, engineering, and customer-facing teams with the clarity and usefulness of analyses.
WHY WORK WITH US AT STOREFORCE
StoreForce is growing quickly – it’s the kind of place you can make a real impact. We thrive on change, collaboration, and trust; And are fueled by a mutual passion for Specialty Retail. At StoreForce you’ll have the chance not only to work with some amazing people, but also with some of the world’s best retail brands.
- We're remote and offer flexibility in your schedule;
- Employer-paid health benefits including dental, prescription drug coverage, and a Health Spending Account;
- RRSP Matching with First Time Home Buyer support*
- Company paid training and professional development
- Extended Long Weekends and Religious Observance Days
- Employee Referral Program
- Spotlight Recognition Bonus Program
- Dedicated Employee Assistance Program (EAP)
- Enhanced family leave policies
- Time off to actively support a charity/volunteer
*Speak with HR for full program details.
StoreForce is an Equal Opportunity Employer and prohibits discrimination and harassment of any kind. We are committed to the principle of equal employment opportunity for all individuals and to providing individuals with a work environment that is diverse and inclusive. This starts by welcoming and encouraging applications from all individuals including those with disabilities. Accommodations are available on request for candidates taking part in all aspects of the selection process.
At StoreForce, we leverage AI tools to support a fair and efficient recruitment process. This may include AI-assisted resume screening to help identify top candidates and AI note taking during interviews. All hiring decisions are made by real people. AI is used only as a supplemental tool to enhance, not replace, human judgment. We never accept or respond to speculative applications from third party recruiters and work only with preferred partners.
Skills Required
- 5+ years of experience in data science or machine learning
- Production models built and used by a product or customers
- Strong Python for data and modeling, including pandas or Polars, scikit-learn, and gradient boosting such as LightGBM or XGBoost
- Strong SQL, including window functions, complex joins, and query optimization
- Experience with time series forecasting, seasonality, holidays, calendar effects, backtesting, and business-aligned error metrics
- Experience building and maintaining tested, version-controlled transformation tables using SQL and Spark or a similar engine
- Production machine learning experience with experiment tracking, model registry, scheduled scoring, monitoring, and retraining using MLflow or an equivalent
- Sound statistics, experimental design, uncertainty analysis, and statistical judgment
- Clear written and spoken communication with engineers, product managers, and customers
- Production experience with Databricks, Unity Catalog, Lakeflow, MLflow, Feature Store, Model Serving, or Metric Views
- Experience with hierarchical and intermittent forecasting, dimensional modeling, incremental processing, and CI/CD for data transformations
- Experience in retail, workforce management, labor scheduling, or store operations analytics
- Experience with multi-tenant SaaS data and customer data isolation
- Experience with optimization methods or causal inference
- Experience with Anthropic Claude, OpenAI, Genie, agent frameworks, evaluation sets, and guardrails
- Graduate degree in statistics, computer science, operations research, another quantitative field, or equivalent experience
What We Do
StoreForce is a Toronto-based SaaS company founded in 2010 by Dave Loat and Chris Matichuk that provides a Retail All-in-One Operations platform built by retailers, for retailers. It helps specialty retailers streamline store operations through workforce management, labor scheduling, time and attendance, real-time KPI performance management, retail execution and task management, and employee engagement, serving leading brands across more than 60 countries so store teams can focus on customers and drive sales.









