Apply on Employer Site

Carvana · 1 day ago

Data Scientist, Production Analytics

Tempe, AZ

Full-time

Onsite

Mid Level

Carvana is revolutionizing the automotive retail industry with innovative approaches to buying and selling cars. The Data Scientist in Production Analytics will develop and maintain predictive models that support decision-making across reconditioning operations, utilizing advanced analytics to drive business outcomes.

AutomotiveAutonomous VehiclesE-Commerce

No H1B

Responsibilities

Building and maintaining predictive models:

Developing neural network models (primarily TensorFlow/Keras) that leverage vehicle characteristics and operational data

Building models that support operational decision-making and performance insights

Maintaining and improving existing production models as business needs evolve

Using LightGBM and linear/logistic regression for benchmarking and explanatory analysis

Implementing hyperparameter optimization and model tuning strategies

Monitoring model performance and identify when recalibration is needed

Performing rigorous exploratory data analysis:

Investigating data quality before training models—validating that data matches operational reality

Grounding expectations to what's actually happening in the business, not just what the data says

Identifying anomalies, edge cases, and data quality issues that could impact model performance

Creating visualizations that communicate patterns and insights to stakeholders

Documenting data validation findings and decisions

Deploying and monitoring production models:

Working with engineering teams to integrate models into operational systems

Tracking prediction accuracy and model drift over time

Developing validation frameworks to ensure models perform as expected

Iterating on models based on production performance and changing business needs

Collaborating and communicating:

Translating business problems into modeling approaches

Explaining model predictions and limitations to non-technical stakeholders

Partnering with operations teams to understand domain context

Documenting model architecture, assumptions, and performance characteristics

Working under the technical direction of our Associate Director with regular guidance and code reviews

Qualification

Neural networksPythonSQLStatistical foundationsTensorFlow/KerasLightGBMData validationGit version controlEagerness to learnSkeptical mindsetCommunication

Required

Bachelor's degree in Computer Science, Statistics, Mathematics, Data Science, or a related quantitative field

Strong understanding of neural networks. You should know how they work in practice, not just theory (architecture design, training dynamics, hyperparameter tuning, regularization)

Proficiency in Python for data science (pandas, numpy, scikit-learn, TensorFlow/Keras or PyTorch)

SQL skills for data exploration and validation (Snowflake experience preferred)

Strong statistical foundations (hypothesis testing, regression, experimental design)

Experience with Git-based version control, branching, and pull requests

Skeptical mindset about data quality—you don't assume data is correct, you validate it

Excellent communication skills to explain technical concepts to non-technical audiences

Eagerness to learn and grow through mentorship and code reviews

A relentless drive to push work into production and see tangible impact