Drimva

General Motors

Senior Software Engineer, Autonomy Evaluation

Remote - United States · Remote/Hybrid · Senior · Full-time · Posted Aug 31, 2026

Experience
5+ years of applied experience; 3+ years evaluating dynamic systems.
Education
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.

About the job

Develops evaluation platforms, metrics, analyses, and reporting to assess autonomous driving performance and support validation and release decisions.

What you'll do

  • Design metrics, statistical and ML analyses, and algorithms to evaluate autonomy software across simulation and on-road runs.
  • Build and maintain evaluation dashboards and reports, including explainable insights into trends, drift, and scenario coverage.
  • Use VLMs and LLMs where appropriate to classify performance, identify critical scenarios, and prioritize validation, with human review as needed.

What they ask for

  • 5+ years of applied experience in robotics or autonomous systems software, data analysis, ML evaluation, or autonomy analytics.
  • 3+ years evaluating dynamic systems using numerical and/or ML approaches, including time-series data, dynamics, and interconnected subsystems.
  • Strong proficiency developing Python in production team environments; proficiency with Pandas, NumPy, SciPy, and plotting/visualization libraries.
  • Comfort working with C++ codebases; demonstrated technical leadership driving architecture, cross-team designs, or complex features.

Nice to have

  • Experience in autonomous driving or field robotics, including simulation and field experiment analysis.
  • Experience with sensor data, large-scale time-series analysis, SQL, ROS or similar frameworks, PyTorch, or AI-assisted development and analytics tools.

Tools

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

AI focus

Develop and apply statistical and ML methods to evaluate autonomy performance and ML components; use VLMs and LLMs where appropriate to classify performance, identify critical scenarios, and prioritize validation. Preferred experience includes AI-assisted development and analytics tools.

Model-written summary · the original posting is authoritative

First seen Oct 28, 2026 · Last verified Nov 5, 2026 (UTC)