Analytics Engineer, AV Safety Engineering

General Motors

4d•Hybrid

About The Position

The Safety Assurance for Effective Autonomous Driving Software (SAFE-ADS) department is part of GM’s Global Product Safety, System, and Certification organization. Our mission is to help GM deliver trustworthy automated-driving products. As the central authority for automated driving system safety, SAFE-ADS brings together experts from across the company to develop and maintain a comprehensive safety case, including safety performance indicators for GM’s automated-driving technologies. GM’s vision is zero crashes, zero emissions, and zero congestion, and autonomous vehicle safety is essential to achieving that vision. The AV Safety Engineering Analytics team supports safety-related decision-making across GM by developing analytics, metrics, and evidence from vehicle, simulation, and external data sources. The team supports both proactive safety monitoring and targeted investigations, and works across stakeholder groups to support engineering, validation, verification, and program decisions by turning complex technical data into usable guidance. The AV Safety Engineering Analytics Engineer is an engineering role with a strong safety data science applied to physical systems focus, centered on developing the analyses, metrics, and evidence used to evaluate automated driving system safety and support decision-making. In this role, you will combine engineering judgment, data analysis, and statistical thinking to transform raw vehicle, simulation, and external data into safety metrics, investigations, and stakeholder-facing insights. You will work with cross-functional partners to define and productionize safety-relevant metrics, establish evidence and sufficiency criteria used to assess system performance and launch readiness, and communicate findings clearly to stakeholders. This role regularly supports systems, safety, testing, and verification activities by helping translate data into decision-useful metrics and evidence. Interactive visualizations and scalable data pipelines are important enablers in this role, helping analyses scale, increasing transparency, and turning complex results into usable stories for decision-making.

Requirements

Bachelor’s degree in Computer Science, Mechanical Engineering, Vehicle Engineering, Physics, or a related field, or equivalent practical experience
5+ years of experience analyzing large-scale driving, vehicle, robotics, or similar engineering data
5+ years of experience in ADAS, autonomous vehicles, robotics, or a related technical domain
Experience with statistics relevant to large-scale engineering data analysis, including sampling, bias management, and experimental design
Experience transforming noisy time-series or sensor data into analysis-ready features or metrics
Strong problem-solving skills and a proactive, learning-oriented mindset
Strong communication and collaboration skills, with the ability to work effectively across technical teams
Strong programming skills in Python and SQL
Experience building and operating cloud-based analytics or data-processing workflows at scale
Experience in some combination of the following is expected: Programming & Frameworks: Python, SQL
Cloud & Big Data: cloud-based large-scale processing including notifications, queuing, serverless functions, event-driven processing, infrastructure as code, containerization, process monitoring, process optimization, identity and access management, and service-to-service access
Statistics: descriptive statistics, managing bias in large data mining activities, experimental design, and sampling strategies
DevOps / Infrastructure as Code: CI/CD, versioning, Docker, Kubernetes, GitHub, Jira, Jenkins, Poetry, Terraform
Data Analysis & Visualization: Tableau, PowerBI, Plotly/Dash, Shiny, Pandas, NumPy

Nice To Haves

Experience analyzing large-scale vehicle motion, driving context, automated-driving performance, or simulation data
Experience with driver behavior modeling, human performance benchmarking, causal inference, or counterfactual modeling techniques
Experience with systems engineering, verification and validation, simulation-based evaluation, scenario analysis, or work that bridges simulation and on-road safety assessment
Experience building stakeholder-facing dashboards or interactive analytics products
Experience with cloud or distributed data platforms, or with DevOps, CI/CD, containerization, or infrastructure-as-code workflows
Publications, conference participation, or other demonstrated engagement in vehicle-safety, safety-analytics, or related technical work

Responsibilities

Define, prototype, and productionize safety and performance metrics for automated driving systems.
Establish analytic approaches and sufficiency criteria that support safety assessment, development decisions, and launch readiness.
Support proactive safety monitoring and targeted investigations tied to specific system-performance or safety questions.
Support systems, safety, testing, and verification stakeholders by comparing real-world and simulation-based results, identifying gaps, and helping improve the representativeness of evaluation methods.
Apply engineering and physics-based methods to process raw signals and derive meaningful representations of vehicle motion, driving context, and system behavior.
Distinguish sensor or pipeline errors from meaningful real-world outliers using engineering judgment and data validation methods.
Create interactive visualizations and reporting artifacts that communicate safety insights clearly, enhance transparency, and reduce barriers to interrogating source data in support of technical decision-making.
Build and maintain analytics infrastructure that supports safety assurance across development, validation, and deployment.
Develop reliable pipelines that ingest, transform, analyze, and publish data from vehicle systems, internal databases, simulation outputs, and external sources.
Optimize analytics code and workflows for scalable, automated cloud execution.