Senior Data Scientist

Clutch

Clutch stands as Canada's largest online platform for used car retail, dedicated to providing a hassle-free purchasing journey with substantial customer satisfaction guarantees. Launched in 2017, Clutch is quickly expanding with the backing of esteemed investors, playing a significant role in transforming consumer automotive purchasing experiences. The Senior Data Scientist at Clutch will lead projects on predictive modeling, enhancing customer experiences and streamlining operations.

In this role you can expect to have the responsibilities:

• Analyze significant datasets to identify impactful trends and guide company strategy.
• Develop predictive models and machine learning algorithms to tackle business challenges.
• Optimize vehicle pricing models to maintain competitiveness through data insights.
• Contribute to the development of a consumer lending engine optimizing credit decision processes.
• Automate reconditioning processes for improved efficiency and reduced costs.
• Design a vehicle recommendation system to enhance customer personalization.
• Communicate data findings to stakeholders with statistical techniques and visualization tools.
• Identify data sources and collaborate with engineers to prepare data for analysis.
• Perform feature engineering, data transformations, and data cleaning.
• Work with diverse data types to enhance analytical precision.
• Maintain efficient data processing workflows.
• Write SQL queries and Python scripts for data transformation and analysis.
• Deploy and monitor machine learning models in production environments.
• Collaborate with engineering and business teams to align models with goals.
• Create interactive dashboards to present actionable data insights.
• Stay updated on data science advancements and incorporate new techniques.
• Document machine learning models and workflows for collaboration.

This role comes with the following benefits:

• Autonomy in career path and ownership of work.
• Competitive compensation and equity incentives.
• Generous time-off program.

This role requires you to have:

• 5+ years in software development with a solid base in software engineering.
• 3+ years in data science, proven in deploying and training ML models.
• Advanced proficiency in Python ML libraries like Scikit-learn, TensorFlow, PyTorch.
• Strong grasp of XGBoost and LightGBM for model enhancement.
• Expertise in data and feature engineering, including cleaning and transformation.
• Experience with cloud data warehouses like Snowflake, Databricks, Redshift.
• Advanced SQL proficiency with complex functionalities.
• Bachelor's degree in data science, statistics, computer science, or similar.
• Strong problem-solving skills translating business needs into solutions.
• Cross-functional collaboration skills.
• Strong communication of complex insights.

You would benefit from having: