Validation Engineer - Context, Semantics & Memory (f/m/x)

- Design and operate knowledge graphs and graph databases that capture domain knowledge, toolchain topology, operational incidents, root-cause analyses and lessons learned. - Build context-engineering pipelines that dynamically assemble, rank and budget the information supplied to LLM-based agents. - Implement feedback loops by coding agents and skills that interact with our toolchain, log outcomes, diagnose failures and write findings back into the knowledge graph. - Develop and maintain ontologies and semantic models for the automotive AI domain, ensuring consistent vocabulary across teams and tools. - Architect agent memory systems with appropriate consolidation and retention mechanisms. - Evaluate and optimise retrieval quality using relevance, coverage, freshness and redundancy metrics, and run experiments comparing retrieval strategies. - Contribute to cost-efficient model selection and context-compression strategies to keep latency low and budgets sustainable at scale.