Senior Software Systems Engineer - Autonomous Vehicles

General Motors•Sunnyvale, CA

1d•$153,200 - $234,100

About The Position

You will be part of a team that drives systematic and data-driven improvements to autonomous vehicle software by designing, implementing, and maintaining robust processes for evaluation and validation. We are looking for a highly motivated individual with excellent analytical skills to own end-to-end execution, improve evaluation methodologies, and communicate insights that establish confidence in the quality of our end-to-end ML stack. In this position, you will work closely with AI/ML engineers, simulation engineers, systems engineers, and data partners to identify, analyze, monitor, and prioritize the signals used to assess performance. You will leverage simulation and on-road data to build scalable processes for evaluating coverage, metrics, uncertainty, and validation confidence. If you are interested in having a major impact on accelerating validation confidence for ML-driven autonomy through creative problem solving, let’s chat!

Requirements

Strong Python programming skills, with experience building clear, maintainable analysis, evaluation, or testing tools.
Experience designing or implementing testing, simulation, or evaluation frameworks for complex software/hardware or cyber-physical systems.
Experience with GitHub, Jira, or equivalent tools.
Demonstrated end-to-end ownership, from defining a problem through delivering and communicating the desired outcome.
A track record of analytical and systems-engineering work involving complex software/hardware systems or ambiguous AI functions.
Experience performing root-cause analysis and applying analytical methods to system or behavioral performance data.
Ability to creatively solve problems with limited supervision, learn quickly, and operate effectively in a fast-paced environment.
Strong cross-functional communication skills, including the ability to communicate data-driven findings to leadership.
Bachelor’s, master’s, or doctoral degree in engineering, physics, applied mathematics, statistics, data science, or a related discipline, or an equivalent combination of education and experience.

Nice To Haves

Experience with autonomous vehicles, ADAS, robotics, or production-grade robotic systems.
Hands-on experience with simulation environments, scenario generation, large-scale test execution, or analysis of simulation results.
Experience with statistical methods for product evaluation, risk assessment, sampling, or confidence analysis.
Experience developing data-driven metrics, scorecards, coverage measures, or regression-detection methods.
Experience with verification and validation, simulation-to-real-world correlation, test automation, or large-scale evaluation systems.
Passion for understanding complex robotics and AI systems and turning their behavior into measurable evidence.

Responsibilities

Define AV evaluation and validation processes from initial concept through implementation, including test-framework requirements, scenario and test-suite design, coverage, metrics, and the evidence needed to assess confidence in system performance.
Design and implement scalable testing and simulation frameworks for test generation, execution, data collection, result aggregation, and reproducible analysis.
Provide hands-on implementation of infrastructure and data solutions to assess confidence in AV performance using simulation and on-road data.
Develop and apply methods to evaluate simulation validity, sim-to-real correlation, and the predictive value of simulation results.
Proactively scope and identify metrics, sampling approaches, and analytical methods needed to improve evaluation workflows and close gaps in evidence.
Contribute to automated triage and root-cause analysis strategies for AV deficiencies, regressions, and uncertainty in an end-to-end stack.
Articulate insights, summaries, limitations, and recommendations to engineers, technical leaders, and other stakeholders based on continuous analysis of AV performance.
Define and maintain scalable processes to identify, monitor, and improve evaluation KPIs and confidence measures.
Help connect continuous-improvement activities to the evidence needed to support safety, systems, and downstream readiness decisions.