Senior Software Engineer, Autonomy Evaluation

What You’ll Do (Responsibilities) 

• Architect and implement metrics and analyses to introspect autonomous driving software performance at interfaces across the autonomy stack; partner closely with autonomy developers and systems engineers. 

• Design and implement analysis algorithms that summarize, aggregate, and cluster metrics produced by simulations and on-road runs of the autonomy stack. 

• Propose and develop new statistical and ML methods to quantify performance and identify patterns of system and subsystem behavior across diverse scenes and operational domains. 

• Develop and apply methods to introspect the operation of ML components in the autonomy stack, including evaluation of perception, prediction, and planning models. 

• Build and maintain autonomy evaluation dashboards and interactive reports that provide clear, explainable insights (e.g., trend analysis, drift detection, scenario coverage) for development, verification, and leadership. 

• Leverage vision-language models (VLMs) and large language models (LLMs), where appropriate, to classify autonomy performance, identify critical scenarios, and prioritize validation efforts, integrating human-in-the-loop review where needed. 

• Maintain a high technical standard through thoughtful system design, code reviews, testing, observability, and adherence to software-engineering best practices. 

• Interface with cross-organizational partners to articulate requirements, resolve handoff issues, and share best practices around evaluation, metrics, and experiment design. 

Your Skills & Abilities (Required Qualifications) 

• 5+ years of applied experience with robotics or autonomous systems software (e.g., sensors, perception, prediction, planning, or control), data analysis, ML evaluation, or autonomy analytics. 

• 3+ years evaluating dynamic systems using numerical and/or ML approaches, including time-series data, state derivatives, dynamics, and interconnected subsystems. 

• Strong proficiency developing Python in production team environments, including testing, performance, and code review. 

• Proficiency with Pandas, NumPy, SciPy, and plotting/visualization libraries for large-scale data analysis and reporting. 

• Comfort working with C++ codebases, including reading, debugging, and instrumenting core algorithms. 

• A strong curiosity to question anomalous data and systematically root-cause discrepancies. 

• Demonstrated technical leadership, including driving architectural decisions, influencing cross-team designs, and owning complex features or services end-to-end. 

• Bachelor’s, Master’s, or PhD in Computer Science, Robotics, Mechanical or Aerospace Engineering, Machine Learning, Data Science, or a related field, or equivalent practical experience

What Will Give You a Competitive Edge (Preferred Qualifications) 

• Experience in autonomous driving or field robotics, including visualizing and interpreting results from simulation and field experiments. 

• Experience evaluating robotics or AV systems using sensor data (e.g., camera, lidar, radar) and large-scale time-series analysis. 

• Strong intuition for data visualization and the ability to decompose high-dimensional metrics into clear, trustworthy, and consumable views for technical and non-technical audiences. 

• Familiarity with statistical modeling, experimental design, and hypothesis testing for autonomy or simulation evaluation; fluency with Pandas, NumPy, SciPy, and visualization tools. 

• Proficiency in C++ and SQL; experience shaping logging, data schemas, and evaluation pipelines for large-scale autonomy testing and performance monitoring. 

• Experience working with ROS or similar robotics/IPC frameworks, log pipelines, and large-scale experiment databases or evaluation platforms. 

• Prior development experience with computational geometry, linear algebra, PyTorch, and ML techniques applied to perception, prediction, planning, or control. 

• Background in modeling agent interaction and contributing to release gating and safety decisions for autonomy systems. 

• Experience leveraging AI-assisted development and analytics tools to improve productivity and evaluation coverage.

#LI-TO1