Senior Data Engineer, Predictive Modeling

Carvana

Confirmed live yesterday High trust

Quick summary

Work type: On-site
Location: Tempe, AZ
Posted: 15 days ago
Freshness: Confirmed live yesterday
Nearby: 99+ roles within 25 mi

Market check

Salary context

How this pay compares to similar roles

Similar $177k

$125k $229k

below market most similar roles pay here above market

This listing doesn't post a salary. Most similar roles pay $135,000–$219,343.

Based on 240 similar postings.

Employer

About Carvana

Carvana is an e-commerce platform for buying and selling used cars, offering customers a fully online purchasing experience with home delivery, financing, and vehicle trade-ins through its network of automated car vending machines and inspection centers.

Carvana currently has 12 open roles on FindRole.

Most-posted roles

View all roles at Carvana

At a glance

TL;DR · Senior Data Engineer, Predictive Modeling

Role Posting Log in to save

The Senior Data Engineer, Predictive Modeling joins the data science and analytics team to engineer intelligent systems that predict consumer behavior and automate complex decisions. You will architect the technical foundation for predictive modeling by refactoring Python code from experimental notebooks into production-ready applications with proper testing and error handling. Key responsibilities include designing scalable data pipelines, developing internal tooling, and building RESTful services. You will manage relational and non-relational data models, create ETL/ELT processes, and ensure data security. The role requires proficiency in Python, SQL, and NoSQL, utilizing technologies such as Docker, Kubernetes, Snowflake, Apache Spark, and Databricks. You will solve business problems like assessing credit risk and optimizing inventory pricing while applying software engineering best practices like CI/CD and version control.

What does a Data Engineer earn?

Median $159000 from 203 postings across 58 companies.

See salary data

Skills

Python SQL NoSQL Docker Kubernetes GCP Azure Snowflake Apache Spark Databricks Git CI/CD Flask NumPy Scikit-learn Jupyter Object-oriented Programming Data Warehousing ETL ELT

What you'll do

Refactor and productionalize Python code from Data Scientists into reliable, maintainable applications with proper testing and documentation.
Design, architect, and maintain robust, scalable predictive modeling data pipelines across the data science ecosystem.
Develop internal tooling and high-availability applications using Docker and Kubernetes to accelerate team productivity.
Create robust ETL/ELT processes to integrate data between different systems while ensuring data quality and lineage tracking.
Design relational and non-relational data models optimized for performance, cost, and maintainability.
Implement security processes to protect sensitive data using certificates, hashing, and permission management.
Translate business requirements into scalable technical solutions and mentor junior engineers on software engineering practices.

What we're looking for

Bachelor's degree in Computer Science, Engineering, Applied Math, Hard Sciences, or a similar field from an accredited institution.
5+ years of experience in data engineering and data warehousing.
2+ years of experience building production systems designed for scalability, availability, and robustness.
Strong coding and application development skills in Python.
Strong software engineering fundamentals including object-oriented design, design patterns, testing methodologies, and code review practices.
Strong experience with at least one cloud service platform provider (AWS, GCP, or Azure).
Fluency in SQL and NoSQL databases with understanding of data modeling and optimization techniques.
Experience with AI/ML tooling and agentic workflow development (preferred).