Senior Software Engineer - Autonomy Evaluation

Build and evolve GM’s autonomy evaluation platforms, including algorithms and dashboards that aggregate simulation metrics and deliver explainable insights. Apply VLMs and LLMs to classify performance and prioritize validation work, partnering across Autonomy, Simulation, Systems, and Safety teams.

• Design and implement analysis algorithms to summarize, aggregate, and cluster simulation metrics
• Build and maintain autonomy evaluation dashboards and reports with trend analysis, drift detection, and scenario coverage
• Leverage VLMs and LLMs to classify autonomy performance and critical scenarios
• Maintain high technical standards via architecture, code reviews, and software-engineering best practices
• Interface with cross-org partners to articulate requirements and resolve handoff issues

The role focuses on data analysis and ML evaluation for autonomy verification using large-scale datasets and statistical methods. You will develop evaluation dashboards with trend analysis and drift detection, and integrate VLM/LLM approaches with human-in-the-loop to identify critical scenarios and improve scenario coverage.

The ideal candidate is a data/ML evaluation engineer with 3+ years of applied experience in data analysis, ML evaluation, or autonomy analytics using large-scale datasets and statistical methods. They can build evaluation dashboards with trend analysis, drift detection, and scenario coverage, and they have experience applying VLMs and LLMs for classifying autonomy performance and critical scenarios.