Senior Engineering Manager, Autonomy Evaluation Applications

Job Description About the Organization Join the team building GM's next generation of autonomous driving, starting with eyes-off driving on the highway and growing toward point-to-point autonomy. The goal is autonomous capability that is safe, reliable, comfortable, and scalable across GM's vehicle portfolio. Autonomy Evaluation helps the AV program figure out where the driver still falls short. Every mile our vehicles drive, on the road or in simulation, carries that signal. We turn it into answers: what is limiting the system, how big each problem is, and what fixing it is worth. Those answers steer what GM's autonomy teams build next and inform software release decisions. Evaluation Applications is the part of Autonomy Evaluation that turns evaluation into decisions. It has four teams. Driver Performance measures overall driving quality. Subsystem Evaluation measures how subsystems such as perception, prediction, planning, and localization affect driving. Scenario Classification builds the scene classifiers that tag what happened in every drive and simulation run. Test Insights turns results into findings for engineering and release reviews.  The Role As Senior Manager of Eval Applications, you will lead these four teams through their managers and tech leads, and own the roadmap, execution, and staffing for how we measure driving quality and turn it into decisions. The work is concrete: using scene classifiers to find simulation tests that don't exercise the behavior they were written to check, or ranking the subsystem failures behind a drop in driving quality so the right team fixes the right thing first. You'll set priorities, build the team, and make sure partner teams trust and act on what we produce. You'll work with the org's principal and staff engineers, who lead evaluation methodology, and with the Software Validation and Safety teams, who use our results in test strategy and release decisions. What You'll Do • Own the strategy, roadmap, and quarterly plans for Eval Applications, tied to the AV program's product milestones and release needs. Decide what the teams build, what they stop, and in what order. • Make evaluation results trusted and used. Partner teams in Autonomy, Simulation, Systems, Safety, and Software Validation should know what each metric and scene classifier means, how accurate it is, and when to rely on it. • Run the loop from observed driving behavior to ranked problems to fixes, so issues found in road and simulation testing get sized, routed to the owning team, and tracked to closure. • Make sure teams can tell quickly and reliably whether a software or model change improved driving, including regression detection that release reviews can depend on. • Set and track org-level measures of evaluation quality and impact, such as classifier precision and recall, time from a new question to a trusted answer, and how often our findings change a decision. • Keep the technical bar high through design reviews, code review standards, testing, and statistically sound analysis, and work with principal and staff engineers on technical direction. • Bring in new methods where they pay off, including VLM- and LLM-based classification and triage with human review, and AI-assisted development across the team. • Turn results into clear recommendations for engineering and executive leadership: what changed, how confident we are, and what to do next. Leadership Responsibilities • Hire, develop, and retain managers, tech leads, engineers, and data scientists, and grow the next layer of leaders. • Lead through managers and tech leads with clear ownership, steady operating rhythms, and real accountability. Run performance management fairly and directly. • Shape team structure and staffing as priorities chang