Salary: 65.000 - 108.000 € per year Requirements: University degree in Computer Science, AI/ML, Systems Engineering, or a related field. 3–5 years of hands-on experience in validation, verification or quality engineering for complex AI, ML or software-intensive systems. Expert-level programming skills in at least one high-level language (C++, Java, Kotlin or Python). Proficiency in AI-assisted development using coding agents such as Claude Code, GitHub Copilot or OpenCode. Understanding of agentic AI architectures, agent patterns and multi-agent interaction. Ability to apply optimization, search or operational-research techniques (genetic/evolutionary algorithms, Bayesian optimisation, Monte Carlo methods) to testing or exploration problems. Experience with automotive software quality processes (e.g. ASPICE, ISO 26262) is a plus. Responsibilities: Build and operate cloud-based validation environments for a multi-agent system that operates across ADAS, Infotainment and backend-service domains – defining test architectures, scenario pipelines, behavioural oracles and regression suites. Design AI-assisted exploration strategies to navigate the semantic search space of the system under test: agent-based probing of behavioural boundaries, adaptive test strategies, and optimization techniques to surface edge cases and failure modes. Develop coverage models and metrics for non-deterministic multi-agent systems and use them to steer test generation and assess release readiness. Establish validation methodologies suited to stochastic AI behaviour: metamorphic testing, property-based testing, adversarial probing and acceptance criteria grounded in confidence intervals rather than binary pass/fail. Build observability and diagnostics tooling for validation runs – distributed tracing, trajectory replay, automated failure clustering and root-cause triage to ensure that discovered issues can be rapidly understood and communicated to the design team. Evaluate and select the LLMs/SLMs that power validation agents and test-generation systems, balancing latency, cost and accuracy for large-scale test campaigns. Close the feedback loop between validation findings and system improvement by structuring discovered failures, coverage gaps and behavioural anomalies into actionable knowledge for the design and context-engineering teams. Technologies: AI Backend Claude Code Cloud Copilot GitHub Java Kotlin Python Security More: At BMW Group, everything starts with passion as we strive to reinvent mobility and bring innovative ideas to the roads. We are focused on building an inter-domain multi-agent system for the intelligent vehicle of the future, where you will play a crucial role in its validation. We offer challenging projects that shape the future of mobility, a variety of personal and professional development opportunities, attractive and performance-related remuneration, a high level of job security, special annual payments, flexible working hours, and many other benefits. Join us and be part of an international team passionate about software quality. last updated 18 week of 2026