Staff Software Engineer, Autonomy Evaluation

General Motors is hiring a Staff Software Engineer to shape and advance the evaluation ecosystem for its autonomous driving technology. The role defines evaluation strategy, develops metrics and analysis methods, leads cross-functional integration into development and release decisions, and communicates system performance and safety insights.

Responsibilities:

• Define the strategy and architecture for metrics and analyses to evaluate autonomous driving software performance across the autonomy stack
• Lead cross-functional efforts with autonomy, systems engineering, simulation, and data teams to embed evaluation into development workflows and release decisions
• Invent and drive new statistical and ML methods, and ML introspection techniques, to quantify performance, detect regressions, and reveal patterns of system behavior at scale
• Own and refine key AV evaluation metrics and KPIs used for readiness and safety decisions; synthesize and present results and tradeoffs to stakeholders; make insights readily available to partner teams through interactive dashboards

Requirements:

• 7+ years applied experience with robotics or autonomous systems software, spanning multiple subsystems from perception through planning and control of the vehicle
• 3+ years leading evaluation of complex dynamic systems using numerical and ML approaches on large-scale time series data
• Proficiency developing Python in production team environments; strong ability to work in large C++ autonomy codebases
• Proven cross-team technical leadership, including defining strategies adopted by multiple teams and influencing system and architecture decisions
• PhD, Masters, or Bachelor's degree in Computer Science, Robotics, Mechanical or Aerospace Engineering, Machine Learning, or a related field
• Experience in autonomous driving or high-stakes field robotics; designing, running, and interpreting large-scale simulation and field experiments
• Deep familiarity with statistical modeling, experimental design, and hypothesis testing for autonomy evaluation; command of Pandas, NumPy, SciPy, and visualization libraries
• Proficiency in C++ and SQL, and experience shaping logging, data schemas, and evaluation pipelines for large-scale autonomy testing
• Experience working with ROS or other IPC, robotics stack logging, and with large-scale experiment databases, including designing or scaling evaluation platforms
• Prior development with computational geometry, linear algebra, PyTorch, and machine learning
• Background in modeling agent interaction and owning or designing release gating criteria and processes for autonomy systems