Quality Data Scientist - Electrical Systems & Field Quality Engineering

Stellantis•Auburn Hills, MI

About The Position

We are seeking a strategic, hands-on Data Scientist to support Warranty Analytics and Programs within our North America quality team. The ideal candidate combines advanced data analytics, predictive modeling, and data manipulation expertise with the ability to communicate complex findings through clear, executive-ready PowerPoint presentations. You will be part of a talented team developing scalable analytics, predictive models, and early-warning capabilities to detect emerging quality trends across large enterprise datasets. This is a fast-paced environment focused on rapid, high-quality delivery for business partners. You will work in a highly collaborative organization that values analytical rigor, speed, innovation, and measurable business impact.

Requirements

Bachelor’s degree in Data Science, Statistics, Mathematics, Engineering, Computer Science, Business Analytics, or a related quantitative field
7+ years of professional experience as a Data Scientist, Advanced Data Analyst, Predictive Analytics Specialist, or similar role
Strong proficiency in Python, SQL, PySpark, and data visualization tools such as Power BI or Palantir Foundry Workshop
Experience working with one or more enterprise data or cloud platforms, such as Palantir Foundry, Snowflake, Databricks, AWS, Azure, or GCP
Demonstrated experience performing advanced data analysis and developing predictive models that support business or operational decisions
Advanced data manipulation skills, including data extraction, cleansing, transformation, joining, feature engineering, validation, and analysis of large, complex datasets
Strong understanding of statistics, exploratory data analysis, hypothesis testing, regression, classification, forecasting, clustering, model evaluation, and applied machine learning
Proven experience delivering end-to-end analytics or data science solutions from requirements gathering and data preparation through validation, deployment, and monitoring
Advanced proficiency in Microsoft PowerPoint, including development of executive-level presentations, analytical storytelling, charts, visual summaries, and clear recommendations for senior leadership
Ability to translate complex analytical findings and model outputs into concise, actionable business insights for technical and nontechnical audiences
Strong communication, stakeholder engagement, problem-solving, prioritization, and cross-functional collaboration skills

Nice To Haves

Master’s degree in Data Science, Statistics, Mathematics, Engineering, Computer Science, Business Analytics, or a related quantitative field
Extensive experience in deep data analysis, predictive analytics, forecasting, and development of models that identify future risks, trends, or outcomes
Demonstrated success converting complex analytical work into persuasive, executive-ready PowerPoint presentations that support decisions and action
Industry experience in automotive, warranty, quality, manufacturing, service operations, or related fields
Familiarity with data modeling, semantic layers, feature stores, and enterprise data platforms
Experience with MLOps concepts, model deployment, versioning, monitoring, explainability, and governance
Hands-on experience with Palantir Foundry, Snowflake Intelligence, Power BI, CoPilot, Anthropic, Gemin, and other forms of OpenAI/GPT or comparable analytics, LLM, and AI platforms
Experience analyzing unstructured data, including text, service narratives, customer complaints, or technical documentation

Responsibilities

Lead and coordinate cross-functional analytics and AI initiatives from problem definition through deployment, ensuring alignment with business objectives, timelines, and measurable outcomes.
Perform deep exploratory, diagnostic, and predictive analysis to identify patterns, relationships, anomalies, emerging risks, and leading indicators within complex datasets.
Build, validate, and deploy predictive models to forecast warranty claims, component failure rates, quality trends, repair demand, and cost exposure.
Apply statistical analysis, machine learning, forecasting, segmentation, and anomaly-detection techniques to solve business and operational problems.
Manipulate, integrate, cleanse, transform, and analyze large structured and unstructured datasets from multiple enterprise sources using Python, SQL, PySpark, and related tools.
Develop robust, repeatable analytical workflows and reusable data products that support scalable decision-making and consistent results.
Partner with business stakeholders to define analytical questions, translate business needs into actionable use cases and technical requirements, and establish success criteria.
Collaborate with data scientists, data engineers, platform teams, and subject-matter experts to improve data accessibility, model performance, scalability, and adoption.
Create compelling, executive-ready PowerPoint presentations that clearly communicate analytical methods, findings, predictions, business implications, risks, recommendations, and next steps.
Develop dashboards, visualizations, and analytical outputs that enable insight adoption, operational action, and performance monitoring.
Present complex analytical findings to technical and nontechnical audiences using concise storytelling, strong visual design, and decision-focused recommendations.
Ensure data quality, lineage, documentation, model transparency, and compliance with enterprise governance requirements.
Monitor model performance and analytical outputs, identify degradation or changing patterns, and recommend model recalibration or process improvements.