Data Scientist

Stellantis Financial Services; Auburn Hills (MI); On-site; USD 110,000 - 150,000; Full time

Job summary

Stellantis Financial Services is seeking a Data Scientist for the Commercial Analytics group to build and scale trusted data science products powering commercial recommendations. You will collaborate with data engineers, analysts, and business teams to design analytics solutions and evaluate model performance.

Ideal candidates are self-motivated and creative, with strong desire to solve real-world problems using data and to promote best practices in model quality and reliability.

Qualifications

• Bachelor’s degree in a quantitative field.
• Automotive experience.
• 5+ years in operations research, systems engineering, data science, or related field.
• Proficiency in Python and SQL.
• Hands-on experience with big data and cloud platforms (Databricks, Snowflake or Spark).
• Exposure to MLOps best practices, including model versioning, monitoring, and deployment pipelines.
• Strong grasp of methods like regression, optimization, neural networks, and clustering.

Responsibilities

• Identify high-impact opportunities for statistical and machine learning use cases with stakeholders.
• Develop defensible, well-documented methodologies for strategic decision-making.
• Communicate complex results clearly to technical and non-technical audiences.
• Define and source data features with data engineers and drive data usage.
• Develop and validate models using regression, optimization, boosting, and neural nets.
• Visualize findings and tell data-driven stories to leadership.
• Maintain production models for scalability and performance.
• Conduct peer code reviews and promote best practices in modeling.
• Collaborate with external and internal resources to support KPI measurement.

Skills

Python

SQL

MLOps

Data visualization

Stakeholder communication

Education

Bachelor's degree

Tools

Databricks

Snowflake

Spark

Job description

Job Overview:

The Commercial Analytics group is looking for a Data Scientist to join our team.Your mission is to build and scale trusted data science products that power commercial recommendations while promoting data science best practices, actionable outputs and a high bar for model quality and reliability.

Data scientists work closely with data engineers, analysts, and business teams to design analytics solutions, implement advanced algorithms and evaluate the performance of use cases. Ideal candidates are self-motivated, inquisitive and creative, with a strong desire to solve real-world problems using data.

In this role, you will:

• Collaborate with business stakeholders to identify high-impact opportunities for statistical and machine learning use cases.
• Develop defensible, well-documented methodologies that stand up to executive scrutiny and support strategic decision-making.
• Communicate complex results clearly to both technical and non-technical audiences.
• Partner with data engineers to define and source relevant data features for modeling as well as drive adoption and a deep understanding of proper data usage.
• Develop and validate models using techniques such as regression, optimization (linear programming, dynamic programming, etc.), gradient boosting, dimensionality reduction and neural networks.
• Communicate findings and recommendations to non-technical audiences through clear visualizations and storytelling.
• Contribute to the maintenance of models in production environments, ensuring scalability and performance.
• Conduct peer code reviews and support best practices in model development and deployment.
• Collaborate with both external and internal resources to support business requirements and key KPI measurement

Basic Qualifications:

• Bachelor’s degree in a quantitative discipline (e.g., Operations Research, Applied Mathematics, Optimization, Data Science or other quantitative field)
• Automotive experience
• Minimum of 5 years of experience in operations research, systems engineering, data science, or a related field
• Proficiency in Python and SQL
• Hands‑on experience with big data and cloud platforms such as Databricks, Snowflake or Spark
• Exposure toMLOps best practices, including model versioning, monitoring, and deployment pipelines
• Strong grasp of mathematical concepts like:
  • Regression (linear, logistic)
  • Linear & Non-Linear Programming
  • Network Flow Models
  • Dynamic Programming
  • Simulation
  • Stochastic Optimization
  • Tree-based models (Random Forest, XGBoost, LightGBM)
  • Neural networks
  • Clustering and dimensionality reduction (e.g., LDA, PCA, Dynamic Time Warping)
• Experience communicating optimization tradeoff and recommendations to executive stakeholders