Staff Engineer, Autonomy Evaluation (VLA)

Role Summary

The Staff Engineer, Autonomy Evaluation (VLA) leads the development of evaluation methods, metrics, and tooling for VLA / VLAM-based automated driving at CARIAD.

This role turns model behavior into clear performance evidence across route-level, scenario-level, and regression testing. You will build the evaluation loop that connects data, simulation, model iteration, and in-vehicle performance, helping the team improve driving quality quickly and make confident technical decisions.

You will work closely with ML, systems, and integration engineers to define how progress is measured for both demo performance and future productization.

• Define and evolve evaluation strategies for VLA / VLAM-based driving performance
• Design metrics and success criteria spanning safety, comfort, robustness, and generalization
• Create benchmarks for route-level, scenario-level, and long-tail/edge-case behavior

• Develop scalable evaluation pipelines across offline logs, simulation, and in-vehicle test results
• Build tooling for dataset slicing, scenario curation, and automated report generation
• Enable reproducible evaluation with clear versioning of data, models, and metrics

• Detect and diagnose regressions across model iterations and software releases
• Establish a structured forensic / root-cause analysis workflow for driving failures and edge cases
• Translate findings into actionable improvements for model training, data collection, and system integration

• Partner with ML and integration engineers to assess model quality and prioritize fixes
• Support release and demo readiness decisions with clear, quantitative evidence
• Communicate results and trade-offs to technical and non-technical stakeholders

• Define best practices for evaluation methodology, metrics hygiene, and reporting
• Mentor engineers and raise the bar for rigor and speed of iteration in the evaluation loop
• Contribute to long-term evaluation architecture for productization

• Systems-level thinking and ability to translate ambiguous driving behavior into measurable outcomes
• Strong analytical skills in benchmarking, regression analysis, and experiment design
• Ability to connect quantitative findings to practical engineering decisions and release readiness
• Strong cross-functional communication skills; comfortable working across teams and time zones
• High ownership mindset with rigor, curiosity, and a bias toward action

• Deep understanding of autonomy evaluation for ADAS / AD, robotics, or embodied AI systems
• Strong experience with performance metrics, benchmarking, regression analysis, and scenario-based validation
• Strong software engineering skills in Python; experience building robust evaluation or data pipelines
• Experience working with simulation, large-scale driving data, or model-in-the-loop evaluation

• Experience with foundation models, VLMs / VLAMs, or end-to-end driving models
• Familiarity with learned evaluators, LLM/VLM-assisted evaluation, or agentic workflows for analysis and triage
• Experience in autonomous driving, robotics, or other safety-critical systems

• Collaborate across time zones; occasional early/late meetings to align with global partners
• Occasional travel as needed for vehicle testing, integration workshops, or demos

• 8+ years of experience in autonomy, robotics, machine learning, or evaluation for complex technical systems
• 3+ years of experience building metrics, validation frameworks, or evaluation pipelines for ML-based systems

• Master’s degree in Computer Science, Robotics, Electrical Engineering, Applied Mathematics, or a related field

• PhD in Computer Science, Robotics, Electrical Engineering, Applied Mathematics, or a related field

Salary range is dependent on factors such as geographical differentials, credentials or certifications, industry-based experience, qualification and training. In the city of Mountain View,…