Consultant AD-Validation PM - SAE L4 Automated Driving & E2E AI Systems
Role details
Job location
Tech stack
Job description
- Define and operationalize holistic validation strategies for E2E AI-based AD systems, combining scenario-based testing, data-driven validation, simulation, and real-world testing
- Translate regulatory, safety and quality requirements (ASPICE, ISO 26262, SOTIF, homologation, ISO PAS 8800) into executable validation concepts, KPIs and release criteria
- Analyze the validation implications of key AD system components, including camera, radar, lidar, sensor fusion, localization, prediction, planning, control, data pipelines and runtime monitoring
- Analyze / orchestrate SiL, HiL, MiL and vehicle-level testing and ensure seamless integration into automated CI/CD pipelines
- Drive scalable validation approaches for AI models (incl. coverage metrics, corner-case detection, data curation strategies, and confidence arguments)
- Define AI model validation KPIs and acceptance thresholds, including scenario coverage, ODD coverage, perception and planning performance, uncertainty calibration, robustness, latency, temporal consistency, rare-event behavior and regression stability
- Align validation scope and evidence with Type Approval and AD Safety Management Systems (AD-SMS)
- Act as central interface between AI development teams, system engineers, toolchain providers, test organizations, and external stakeholders (e.g. authorities, partners, suppliers)
- Manage stakeholders at program and management level, including reporting, risk management, decision preparation and escalation
- Proactively identify validation risks related to AI behavior, operational design domain (ODD) boundaries, and system interactions
Requirements
Do you have experience in CI/CD?, * A university degree in Engineering, Computer Science, Artificial Intelligence or a related field
-
Solid understanding of AI/ML concepts for autonomous driving, including E2E vision-heavy approaches, data-driven development and AI-specific validation challenges
-
Deep understanding of the validation challenges of SAE Level 4 automated driving systems, including ODD definition, scenario coverage, residual risk assessment, safety case development and evidence-based release decisions
-
Hands-on experience with Simulations, SiL and HiL testing, ideally integrated into automated CI/CD environments
-
Strong technical understanding of AD system architectures, including modular pipelines, E2E AI models and hybrid architectures, as well as their impact on validation strategy and safety argumentation
-
Practical knowledge of camera, radar and lidar sensor characteristics, sensor fusion principles, calibration, synchronization, degradation effects and typical failure modes relevant for AD validation
-
Proven track record in high-reliability industries (automotive, aerospace, medical), with deep exposure to ASPICE, ISO 26262, SOTIF and homologation processes
-
Strong analytical and structuring skills to translate abstract safety, regulatory and AI risks into concrete validation strategies
-
Ability to work proactively and independently in agile, cross-functional teams, lead validation initiatives, and align multiple internal and external stakeholders