Staff Engineer, Autonomy Evaluation (VLA)

We are CARIAD, an automotive software development team with the Volkswagen Group. Our mission is to make the automotive experience safer, more sustainable, more comfortable, more digital, and more fun. To achieve that we are building the leading tech stack for the automotive industry and creating a unified software platform for over 10 million new vehicles per year. We’re looking for talented, digital minds like you to help us create code that moves the world. Together with you, we’ll build outstanding digital experiences and products for all Volkswagen Group brands that will transform mobility. Join us as we shape the future of the car and everyone around it.

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.

Role Responsibilities:

Evaluation Strategy & Metrics

• 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

Evaluation Pipelines & Tooling

• 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

Regression Detection & Failure Analysis

• 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

Cross-Functional Partnership & Decision Support

• 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

Technical Leadership & Standards

• 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

General Skills:

• 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

Required Specialized Skills:

• 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

Desired Skills:

• Experience with foundation models, VLMs / VLAMs, or end-to-end driving models