Sr. Data Engineer, Ops Decision Systems

Responsibilities

• Design, build, and operate production simulation and optimization systems.
• Develop Python-based simulation models in Databricks as a member of a highly technical team designing interconnected models.
• Work in Git-versioned repositories with merge-request review, automated testing, and CI/CD pipelines (GitLab), and apply AI-assisted and agentic development workflows as a standard part of the engineering stack.
• Statistical and optimization model development.
• Design, validate, and maintain the models that drive operational decisions: reconditioning capacity and throughput models, operating-expense models, inventory allocation optimization, and disposition-timing models.
• Apply statistical, machine learning, and optimization methods, with backtesting and production performance monitoring.
• Operations data products and pipelines.
• Build and maintain the data models and pipelines that describe operational performance, covering inventory state, auction outcomes, reconditioning throughput and cost, logistics, and allocation, with data contracts, tests, and documentation that allow downstream decision systems and planning tools to consume them reliably.
• AI-augmented engineering.
• Network and capacity scenario engineering.
• Model the prioritization of units for reconditioning, the routing of vehicles toward demand, and the strategic deployment of inventory to maximize profit and stability.
• Work with customer-focused colleagues to integrate demand signals, and operationalize recommendations with Remarketing operations leadership, internal service and delivery partners, and external third-party partners.

Requirements

• Proficiency with Python, SQL, and Databricks (or equivalent warehouse/lakehouse platform); experience with dbt or equivalent transformation frameworks.
• Experience with Git-based engineering workflows, code review, and CI/CD pipelines (GitLab or equivalent).
• Demonstrated experience owning production data infrastructure end-to-end, including data modeling, pipeline orchestration, testing, and deployment.
• Demonstrated ability to design and validate applied simulation and optimization models, including capacity modeling, operational optimization, or multi-variable simulation over multi-year horizons.
• Experience reasoning about supply/demand constraints, depreciation mechanics, holding costs, and operating expense, and translating operational decisions into dollar-denominated outcomes.
• Demonstrated ability to translate ambiguous operational questions into production data products and durable models.

Qualifications

• Bachelor’s degree or higher in a quantitative or technical field (Computer Science, Data Science, Statistics, Mathematics, Industrial Engineering, or similar).
• Experience applying machine learning or deep learning methods to capacity, logistics, or operational forecasting problems.
• Experience integrating external APIs and third-party data sources into production data systems.
• Experience with AI-assisted development workflows and agentic coding tools.
• Experience in automotive, marketplace, e-commerce, supply chain, or adjacent operations domains.
• Familiarity with BI and analytics tools such as Hex, Looker, or equivalent.