Principal Engineer, Autonomy Evaluation

GM•Sunnyvale, CA

About The Position

Join General Motors’ Autonomy Evaluation team, which supports the development of safe, reliable, comfortable, and scalable autonomous driving across GM’s vehicle portfolio. The team analyzes miles driven on roads and in simulation to identify system limitations, quantify their impact, and guide engineering priorities and software release decisions. It works closely with Autonomy, Simulation, Systems, Safety, and Software Validation. The Principal Engineer will own evaluation of autonomous driving behavior, from overall driving quality to individual subsystems. The role involves developing methods that other teams adopt, setting priorities across organizations, producing evidence used in release decisions, and prototyping and delivering code. This is a senior individual-contributor position with no direct reports, with responsibility for mentoring Staff and Senior engineers. GM describes its vision as a world with Zero Crashes, Zero Emissions, and Zero Congestion, and says it is committed to an inclusive workplace and equal employment opportunity. The role includes eligibility for a company vehicle evaluation program after successful completion of a motor vehicle report review.

Requirements

At least 10 years of experience in autonomous systems, robotics, ML evaluation, applied data science, or a related area, with a record of turning analysis into decisions and shipped improvements.
Track record of creating evaluation or measurement methods adopted beyond the candidate’s own team.
Deep experience designing statistically sound evaluations of dynamic systems, including sampling, confidence intervals, experimental design, hypothesis testing, and classifier precision and recall on time-series data.
Strong production Python and SQL skills, including testing and code review.
Ability to start from raw observations, define and size problems, and drive them to resolution using trusted data.
Proven ability to influence without authority, align peers, partner teams, and leadership on technical direction, and secure commitments from organizations the candidate does not manage.
Strong stakeholder-engagement skills and ability to build trusted relationships with Autonomy, Simulation, Safety, Software Validation, and other partners.
Experience mentoring senior engineers through design reviews and written technical direction.
Ability to turn ambiguous questions and uncertain results into clear recommendations for executive, engineering, and cross-functional audiences.
Bachelor’s, Master’s, or PhD in Computer Science, Robotics, Mechanical or Aerospace Engineering, Machine Learning, Statistics, Data Science, or a related field, or equivalent practical experience.

Nice To Haves

Experience in autonomous driving or field robotics, including large-scale analysis of driving logs and AV sensor data such as camera, lidar, and radar from simulation and on-road testing.
Experience producing evaluation evidence for validation and release decisions, ideally for driver-assistance or automated-driving products.
Experience applying VLMs or LLMs to event classification, triage, or scenario discovery.
Experience with ML model interpretability, such as attribution, ablations, or embedding analysis.
Strong data-visualization instincts and ability to turn high-dimensional metrics into clear, trustworthy views.
Familiarity with C++, especially for reading or contributing to autonomy stack code.

Responsibilities

Set the multi-year technical direction for autonomy evaluation, choosing which questions and methods to prioritize and which methods to retire.
Develop ways to evaluate overall driving behavior, including learned or VLM-based driving-quality judges, comparison with expert human driving, counterfactual and closed-loop analysis, and discovery of unknown failure modes.
Define evaluations and meaningful metrics for perception, prediction, planning, localization, and other subsystems, including learned components.
Trace poor driving outcomes to the subsystem or interaction that caused them, and measure how subsystem errors affect driving outcomes.
Determine whether software or model changes improve driving, including regression detection and version-to-version comparisons.
Translate observed behavior into measured and ranked problems using metrics and scene classifiers; build a Pareto view of problems and drive fixes with the responsible teams.
Ensure evaluation rigor through appropriate sampling, statistical confidence, metric validity, and agreement between simulation and road results.
Make assumptions and limitations explicit, and resolve difficult disagreements between evaluation signals.
Provide clear recommendations to engineering teams and leadership about changes, confidence, and next steps.
Prototype and deliver code, including production-quality implementations.
Mentor Staff and Senior engineers through research and design reviews and written technical direction.

Benefits

Medical insurance
Dental insurance
Vision insurance
Health Savings Account
Flexible Spending Accounts
Retirement savings plan
Sickness and accident benefits
Life insurance
Paid vacation and holidays
Tuition assistance programs
Employee assistance program
GM vehicle discounts
Company vehicle evaluation program, subject to successful completion of a motor vehicle report review