Staff Software Engineer - Autonomy Evaluation

What you'll do

• Define evaluation metrics, analyses, and architecture for autonomous-driving software performance.
• Lead cross-functional efforts to integrate evaluation into development workflows and release decisions.
• Develop statistical and ML methods and introspection techniques, and present evaluation results through dashboards.

What they ask for

• 7+ years of applied robotics or autonomous-systems software experience spanning multiple subsystems from perception through vehicle planning and control.
• 3+ years leading evaluation of complex dynamic systems using numerical and ML approaches on large-scale time-series data.
• Production Python proficiency and ability to work in large C++ autonomy codebases.
• Cross-team technical leadership, including defining strategies adopted by multiple teams and influencing system and architecture decisions.

Nice to have

• Experience in autonomous driving or high-stakes field robotics, including large-scale simulation and field experiments.
• Familiarity with statistical modeling, experimental design, hypothesis testing, and tools including Pandas, NumPy, SciPy, and visualization libraries.

Tools

Python, C++, Pandas, NumPy, SciPy, SQL, ROS, PyTorch

AI focus

Develops statistical and ML methods and ML introspection techniques to evaluate autonomous-driving performance, quantify results, detect regressions, and identify patterns in system behavior.