Senior Data Engineer - Vehicle Quality Engineering

General Motors; Warren (MI); Hybrid; USD 125,000 - 169,000; Full time

Benefits offered by this job

Health and wellbeing benefit programs

Health Savings Account

Flexible Spending Accounts

Retirement savings plan

Sickness and accident benefits

Life insurance

Paid vacation & holidays

Tuition assistance programs

Employee assistance program

GM vehicle discounts

Bonus Potential

Job summary

General Motors in Warren, MI seeks a senior analytics engineer to build and operationalize analytics and anomaly detection that improve vehicle, software, and product-quality outcomes.

You will collaborate with subject matter experts to define metrics, thresholds, and decision criteria; run unbiased analyses across vehicle, software, warranty, diagnostic, fleet, and product-quality data; deploy anomaly-detection solutions and end-to-end pipelines.

Qualifications

• Bachelor’s degree in Data Science, Statistics, Computer Science, Engineering, Mathematics, or related field, or equivalent practical experience.
• 7+ years of data engineering/development or related experience.
• Experience applying statistical analysis and/or ML methods (anomaly detection, forecasting, classification) to real-world problems.
• Strong Python skills for data analysis, algorithm development, automation, and production workflows.
• Experience querying, transforming, validating, and analyzing large datasets using SQL and modern data technologies.
• Ability to take an analytical solution from problem definition through testing, deployment, monitoring, and improvement.
• Experience communicating analytical results to stakeholders with varying technical expertise.
• Strong data-quality mindset and ownership, with ability to deliver in cross-functional teams.

Responsibilities

• Collaborate with subject matter experts to define metrics, analytical objectives, thresholds, and decision criteria.
• Run unbiased analyses to uncover trends, anomalies, relationships, and risks across vehicle, software, warranty, diagnostic, fleet, and product-quality data.
• Design, test, and deploy anomaly-detection and monitoring algorithms for issues impacting customers.
• Build end-to-end analytical pipelines delivering insights, dashboards, alerts, and operational workflows from raw data.
• Create alerting solutions for rapid response to high-priority vehicle and product issues.
• Establish validation methods using historical data, testing, domain expertise, and real-world observations.
• Communicate findings and recommendations to technical and non-technical audiences.
• Improve performance, scalability, and cost efficiency through model, query, pipeline, and architecture improvements.
• Standardize analytical processes and adopt modern Azure-based technologies to reduce data handling complexity.
• Support launches with readiness insights and analytical tools.
• Document methods, data lineage, operating procedures, and known limitations for maintainability.

Skills

Python

SQL

Azure

Databricks

Data pipelines

Git-based workflows

Education

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

Equivalent practical experience

Tools

Azure Data Factory

Databricks

Git

CI/CD

Databricks Asset Bundles

Job description

Build and operationalize analytics and anomaly detection that improve vehicle, software, and product-quality outcomes.

Responsibilities

• Collaborate with subject matter experts to define metrics, analytical objectives, thresholds, and decision criteria.
• Run unbiased analyses to uncover trends, anomalies, relationships, and emerging risks across vehicle, software, warranty, diagnostic, fleet, and product-quality data.
• Design, test, and deploy anomaly-detection and pre-emptive monitoring algorithms for issues that impact customers.
• Build end-to-end analytical pipelines that deliver insights, dashboards, alerts, and operational workflows from raw data.
• Create alerting solutions so internal customers can respond quickly to high-priority vehicle and product issues.
• Establish validation methods using historical data, controlled testing, domain expertise, and, when appropriate, real-world observations.
• Communicate findings, assumptions, limitations, and recommendations to technical and non-technical audiences.
• Improve performance, scalability, reliability, and cost efficiency through model, query, pipeline, and architecture improvements.
• Reduce complexity and redundant data handling by standardizing analytical processes and adopting modern Azure-based technologies.
• Support vehicle and software launches with readiness insights and analytical tools.
• Document analytical methods, data lineage, operating procedures, and known limitations for maintainability and cross-team adoption.
• Deliver critical analytics features with clear acceptance criteria and production support plans for internal customers.
• Launch or improve pre-emptive monitors to detect emerging vehicle, software, and product-quality concerns earlier than reactive approaches.
• Provide trusted dashboards and alerts that enable real-time, data-driven decisions for engineering, quality, warranty, and launch teams.
• Improve ingestion, query, and dashboard performance while reducing manual preparation and cloud-resource costs.
• Integrate additional signals (warranty, diagnostic, software, operational data) to increase detection confidence and business context.
• Own outcomes across discovery, development, deployment, support, and ongoing improvement.
• Troubleshoot production and analytics issues quickly and follow work through completion.
• Improve usability and maintainability of existing analytics products.
• Contribute reusable patterns and mentoring that increase the impact of the broader analytics organization.
• Demonstrate measurable customer value through reduced manual effort, faster investigation, improved launch readiness, or earlier risk mitigation.
• Increase adoption by partnering with software domains and operational teams to understand how insights are used and where capabilities should expand.
• Strengthen analytical governance with documented definitions, validation methods, data quality checks, and repeatable operating practices.

Key Analytical Approach (as performed)

• Select appropriate analytical methods based on business questions, data limitations, and decision context.
• Test assumptions and validate results using statistical and domain-informed practices.
• Balance detection sensitivity, false positives, explainability, and operational usefulness.
• Start from how internal customers make decisions and design solutions around that workflow.
• Convert complex data into clear, actionable insights and build trust through responsiveness, transparency, and data quality.

Preferred Focus Areas / Examples

• Develop pre-emptive detection for emerging product-quality issues and other customer-impacting patterns.
• Build algorithms that summarize suspect behavior and support engineering teams in identifying problematic charging conditions or stations.
• Create dashboards and alerts for timely visibility into VIP vehicle concerns, launch readiness, fleet behavior, and production risks.

Requirements

• Bachelor’s degree in Data Science, Statistics, Computer Science, Engineering, Mathematics, or a related field, or equivalent practical experience.
• 7+ years of data engineering/development or related experience.
• Experience applying statistical analysis and/or machine learning methods (anomaly detection, forecasting, classification, or related) to real-world business or engineering problems.
• Strong Python skills for data analysis, algorithm development, automation, and production-oriented data workflows.
• Experience querying, transforming, validating, and analyzing large and complex datasets using SQL and modern data technologies.
• Ability to take an analytical solution from problem definition through testing, deployment, monitoring, and continuous improvement.
• Experience communicating analytical results and recommendations to stakeholders with different technical expertise.
• Strong data-quality mindset, including investigating discrepancies, assessing assumptions, and explaining limits.
• Proven ownership, judgment, responsiveness, and ability to deliver to completion in a cross-functional environment.

Technologies

• Python
• SQL
• Azure
• Data Factory
• Databricks
• Git-based workflows
• CI/CD
• Databricks Asset Bundles

Benefits

• Health and wellbeing benefit programs including medical, dental, vision
• Health Savings Account
• Flexible Spending Accounts
• Retirement savings plan
• Sickness and accident benefits
• Life insurance
• Paid vacation & holidays
• Tuition assistance programs
• Employee assistance program
• GM vehicle discounts
• Bonus Potential: incentive pay program with payouts based on company performance, job level, and individual performance

Compensation

• Expected base compensation: USD 125,000 - 168,650 per year
• Bonus Potential: incentive pay program with payouts based on company performance, job level, and individual performance

Hybrid Work Expectations

• Report to Warren Global Technical Center or Austin Technical Center three times per week, at minimum

Additional Eligibility Requirement

• GM does not provide immigration-related sponsorship for this role
• Do not apply if you will need GM immigration sponsorship now or in the future

Measures of Success

• Accuracy, precision, recall, timeliness, and operational usefulness of deployed detection solutions
• Adoption and satisfaction among engineering, quality, warranty, and launch-readiness customers
• Reduction in time to investigate issues, prepare meetings, extract data, or respond to high-priority risks
• Reliability, performance, scalability, maintainability, and cost efficiency of production analytics products
• Completion of committed critical features and effective production support
• Quality of documentation, data definitions, validation practices, and knowledge sharing
• Demonstration of GM behaviors: Own the Outcome, Think Customer, Innovate Now, Win with Integrity, Commit to Customers, and One Team

What Can Give You a Competitive Advantage (Preferred Qualifications)

• Experience with Azure data services, Data Factory, Databricks, data pipelines, workflow orchestration, or comparable cloud technologies
• Experience building operational dashboards, alerting tools, or decision-support products for engineering, quality, warranty, manufacturing, fleet, or customer-facing teams
• Experience working with vehicle, telematics, diagnostic, warranty, software-version, and/or product-launch data
• Experience with time-series data, event data, fleet-level analysis, VIN-level investigation, or software-quality monitoring
• Experience with modern deployment practices such as Git-based workflows, CI/CD, or Databricks Asset Bundles
• Familiarity with data modeling, data lineage, reusable analytical patterns, and scalable solution design
• Experience evaluating whether AI/ML methods improve detection quality while controlling false positives and operational burden
• Experience mentoring peers, sharing technical best practices, or leading work across organizational boundaries