Data Scientist

UpshopMississaugaEngineering

Apply on company site

Opens the official Upshop careers page

Salary

$120K - 140K CAD

Job type

Full-time

Experience

Mid

Posted

9 Oct 2026

Status

Open · checked 7d ago

About this role

This position suits an engineering-focused data scientist who enjoys building and maintaining production-grade forecasting systems within the Databricks environment. Located in Mississauga, this full-time role involves creating retail demand forecasting and optimization models that run reliably in enterprise production.

Role Overview

Upshop is hiring a Data Scientist for a full-time position based in Mississauga. The professional in this role connects applied data science with machine learning engineering, taking full ownership of item-store level demand forecasts and downstream replenishment engines. Success in this position is measured by forecast accuracy and the stability of low-latency pipelines running natively on the Databricks Lakehouse.

Key Responsibilities

Design, tune, and operationalize time-series forecasting engines and supply chain optimization logic utilizing distributed Python, PySpark, and tree-based ensemble methods.

Create and manage automated training and batch inference pipelines using Databricks Workflows and Jobs, alongside MLflow for model registry and experiment tracking.

Collaborate closely with Product teams to translate business requirements into technical specifications and define operational service-level agreements.

Partner with Data Engineering to establish data contracts, implement schema validations, and optimize data ingestion patterns from upstream Delta tables.

Deploy pipeline quality controls, such as pre-inference validation gates and automated alerting systems, to maintain production software standards.

Monitor pipeline health, track runtime performance, and identify feature drift, target drift, and forecast degradation across retail catalogs.

Write modular, testable code following version control practices, automated CI/CD checks, and unit testing protocols using pytest.

Requirements

Practical experience building, tuning, and deploying gradient boosted decision trees, specifically LightGBM and CatBoost, on tabular and time-series data.

Understanding of time-series retail forecasting challenges, including seasonality, promotional uplifts, calendar events, trends, and intermittent demand patterns.

Background working within the Databricks ecosystem, managing multi-task Databricks Workflows and Jobs, navigating Delta Lake, and utilizing MLflow.

Proficiency in Python and PySpark for distributed data processing, feature engineering, and large-scale dataset transformations.

Familiarity with software engineering fundamentals, clean code principles, virtual environments, automated testing with pytest, and Git workflows.

Nice to Have

Knowledge of inventory optimization mechanics like safety stock calculations, lead time variability, and reorder point modeling.

Experience utilizing advanced Databricks features such as Delta Live Tables, Photon compute engine, and Unity Catalog for data governance.

Implementation background in explainable AI methods, including TreeSHAP, within production batch scoring jobs.

Experience configuring continuous integration pipelines using tools like GitHub Actions for automated deployment into Databricks workspaces.

Skills and Tools

Python

PySpark

LightGBM

CatBoost

Databricks

Databricks Workflows and Jobs

MLflow

Delta Lake

Delta Live Tables

Unity Catalog

Photon

Pytest

Git

TreeSHAP

GitHub Actions

Salary and Benefits

The estimated pay range for this role is $120,000 to $140,000 CAD.

Starting compensation is determined by permissible factors including skills, experience, and geographic location.

About the Company

Upshop builds retail forecasting and optimization models designed for operational reliability on the Databricks Lakehouse, partnering closely across product and data engineering teams.

How to Apply

Interested candidates should apply on the official company careers page.

Skills and tech stack

Python PySpark LightGBM CatBoost Databricks MLflow Delta Lake Delta Live Tables Unity Catalog Photon pytest Git TreeSHAP GitHub Actions MLOps Machine Learning

Questions candidates ask

What is the location of the Data Scientist position?

The role is located in Mississauga.

What is the salary range for this job?

The estimated pay range is $120,000 to $140,000 CAD, determined by factors such as skills, experience, and geographic location.

What machine learning libraries are required for the role?

The posting requires hands-on experience with tree-specifically gradient boosted decision trees like LightGBM and CatBoost.

Which platform is used for running the machine learning pipelines?

Pipelines run natively on the Databricks Lakehouse, utilizing Databricks Workflows and Jobs, Delta Lake, and MLflow.

How should I apply for this position?

Candidates should apply on the official company careers page.

Ready to apply?

The application is on the official Upshop careers page.

Apply on company site