Senior Data Scientist

Clutch; Toronto; On-site; CAD 90,000 - 130,000; Full time

Job summary

Clutch, Canada's leading online used car retailer, seeks a Data Scientist to optimize operations through data analysis and machine learning. Join a dynamic team to enhance customer experiences and drive impactful business decisions utilizing advanced data science techniques.

Benefits

Autonomy & ownership

Competitive compensation and equity incentives

Qualifications

• 5+ years experience as Software Developer/Engineer.
• 3+ years in data science with machine learning models.
• Strong background in data and feature engineering.

Responsibilities

• Analyze large datasets to inform business strategies.
• Build and deploy machine learning models.
• Develop pricing models for vehicle acquisition.

Skills

Python

Data Engineering

Machine Learning

SQL

Education

Bachelor's degree in data science, statistics, computer science, or related field

Tools

Scikit-learn

TensorFlow

PyTorch

XGBoost

LightGBM

Snowflake

Databricks

Redshift

Job description

Clutch is Canada's largest online used car retailer, delivering a seamless, hassle-free car-buying experience to drivers everywhere. Customers can browse hundreds of cars from the comfort of their home, get the right one delivered to their door, and enjoy peace of mind with our 10-Day Money-Back Guarantee… and that's just the beginning.

Named one of Canada's top growing Companies two years in a row and also awarded a spot on LinkedIn's Top Canadian Startups list, we're looking to add curious, hard-working, and driven individuals to our growing team.

Headquartered in Toronto, Clutch was founded in 2017. Clutch is backed by a number of world-class investors, including Canaan, BrandProject, Real Ventures, D1 Capital, and Upper90. To learn more, visit clutch.ca.

What you'll do :

Clutch is looking for a Data Scientist to help drive data-driven decision-making across our business. You'll work on analyzing data, building predictive models, and deploying machine learning solutions to improve operations and customer experiences.

• Analyze large datasets to extract meaningful patterns, trends, and insights that inform business and operational strategies.
• Build, validate, and deploy predictive models and machine learning algorithms to solve key business challenges.
• Develop and optimize pricing models for vehicles, ensuring competitive and data-driven pricing strategies. These models currently purchase > 1 million vehicles per day, with no human intervention.
• Contribute to the development of a loan engine that powers our new consumer lending project, helping to optimize credit decisioning.
• Create automation solutions for reconditioning to improve efficiency and reduce costs.
• Design and implement a vehicle recommendation algorithm that enhances customer experience and personalization.
• Use statistical techniques and data visualization to effectively communicate findings to stakeholders.
• Identify relevant data sources and collaborate with data engineering teams to gather and preprocess data for analysis.
• Perform feature engineering, data transformation, and data cleaning to prepare datasets for modeling.
• Work with structured and unstructured data from various sources to enhance analytical accuracy.
• Develop and maintain data processing workflows, ensuring efficient mapping, transformation, and enrichment of data.
• Write SQL queries and Python scripts to transform, analyze, and model data for business impact.
• Deploy machine learning models into production environments, monitoring their performance and optimizing them over time.
• Collaborate with software engineers, analytics engineers, and business stakeholders to ensure models align with business goals.
• Create and maintain interactive dashboards to present data insights in a clear, actionable format.
• Stay up to date with advancements in data science, machine learning, and AI technologies, experimenting with new techniques to enhance existing workflows.
• Write clear documentation for ML models, pipelines, and workflows to support collaboration and reproducibility.

What we're looking for :

• 5+ years of experience as a Software Developer / Engineer with a strong software development background.
• 3+ years of experience in data science, with a proven track record of deploying and training machine learning models.
• Advanced proficiency in Python ML libraries such as Scikit-learn, TensorFlow, and PyTorch for regression, classification, clustering, and deep learning techniques.
• Strong understanding of gradient boosting frameworks such as XGBoost and LightGBM for building high-performance models.
• Expertise in data and feature engineering, including data cleaning, normalization, transformation, and selecting relevant features from raw data.
• Experience working with large-scale datasets within cloud data warehouses such as Snowflake, Databricks, or Redshift.
• Advanced SQL skills, including joins, subqueries, window functions, common table expressions (CTEs), aggregations, complex string manipulations, stored procedures, and functions.
• Bachelor's degree in data science, statistics, computer science, or a related field.
• Strong problem-solving skills and ability to translate business challenges into data-driven solutions.
• Ability to work cross-functionally with engineers, analysts, and business teams to drive impact.
• Strong communication skills, with the ability to present complex insights in an accessible way.

Why you'll love it at Clutch :

• Autonomy & ownership create your own path, and own your work
• Competitive compensation and equity incentives!