<h1> Validation Engineer - Context, Semantics &amp; Memory (f/m/x) </h1> <p> Referenznummer: 26784_185161 </p> <p> Standort: München, BY, DE, 80809 </p> <p> Unternehmen: BMW Group </p> <p> INNOVATION IS IMAGINING WHAT NO ONE ELSE CAN. </p> <p> At the BMW Group, everything starts with passion. It turns a profession into a vocation. It drives us to keep reinventing mobility and bring innovative ideas onto the roads. Enthusiasm for joint projects turns a team into a strong unit where every opinion is valued. It is only when expertise, highly professional processes and enjoyment of work unite that we can shape the future together. </p> <p> Our platform teams build AI-based toolchains that simulate, reprocess and train models on petabyte-scale automotive data – and we increasingly rely on agentic AI to operate, maintain and improve these toolchains. The glue that makes agents effective is context: the right knowledge, delivered at the right time, in the right shape. We are looking for an engineer who can design and evolve the knowledge-management and context-engineering backbone that powers both our product (an inter-domain multi-agent vehicle system) and our internal development toolchain. </p> <p> What awaits you? </p> <ul> <li> You design and operate knowledge graphs and graph databases that capture domain knowledge, toolchain topology, operational incidents, root-cause analyses and lessons learned – enabling graph-based retrieval across the organization. </li> <li> Further, you build context-engineering pipelines that dynamically assemble, rank and budget the information supplied to LLM-based agents. </li> <li> Also, you implement feedback loops: coding agents and skills that interact with our toolchain log outcomes, diagnose failures and write findings back into the knowledge graph, making the system progressively more capable. </li> <li> It is your responsibility to develop and maintain ontologies and semantic models for the automotive AI domain – sensor configurations, simulation scenarios, data-pipeline topology, model lineage – ensuring consistent vocabulary across teams and tools. </li> <li> You architect agent memory systems (working, episodic, semantic) with appropriate consolidation and retention mechanisms so that long-running agent sessions retain useful experience without context-window bloat. </li> <li> In addition, you evaluate and optimise retrieval quality using relevance, coverage, freshness and redundancy metrics, and run experiments comparing retrieval strategies (dense, sparse, graph, hybrid). </li> <li> You contribute to cost-efficient model selection and context-compression strategies (prompt compression, semantic caching, model routing) to keep latency low and budgets sustainable at scale. </li> </ul> <p> What should you bring along? </p> <ul> <li> University degree in Computer Science, Information Science, AI/ML, or a related field. </li> <li> 1-3 years of professional experience in knowledge management, knowledge-graph engineering or context engineering for AI/LLM systems. </li> <li> Expert-level programming skills in at least one high-level language (C++, Java, Kotlin or Python). </li> <li> Proficiency in AI-assisted development using coding agents such as Claude Code, GitHub Copilot or OpenCode. </li> <li> Hands-on experience building and querying knowledge graphs (RDF/SPARQL or property graphs) and integrating them with LLM-based retrieval (e.g. GraphRAG, hybrid search). </li> <li> Experience with systems design, particularly for knowledge-intensive or retrieval-heavy architectures. </li> <li> Familiarity with agent memory architectures, ontology design, semantic modelling, graph-based analytics, entity resolution or knowledge-graph embeddings. </li> </ul> <p> You enjoy working in an international team and are passionate about software quality? Apply now! </p> <p> Find out more about Artificial Intelligence at the BMW Group here. </p> <p> Note: Please apply exclusively online via our career portal. Applications via other channels (esp. e-mail) cannot be considered. </p> <p> What do we offer? </p> <ul> <li> Challenging projects with which we are shaping the mobility of tomorrow together. </li> <li> Wide range of personal and professional development opportunities. </li> <li> Attractive, fair and performance-related remuneration. </li> <li> High level of job security. </li> <li> Annual special payments such as vacation pay, Christmas bonus, and profit sharing. </li> <li> Flexible working hours including 6 weeks annual leave and overtime compensation. </li> <li> Discounted BMW &amp; MINI conditions. </li> <li> Many other benefits at bmw.jobs/benefits </li> </ul> <p> Start date: from now on </p> <p> Type of employment: unlimited <br/> Working hours: Full-time </p> <p> If you apply, the next stages of the recruiting process include an online test followed by technical interviews with the hiring manager (either virtual or in person). </p> <p> You can find helpful tips on your application and the application process here. </p> <p> At the BMW Group, we place great importance on equal treatment and equal opportunities. Our recruiting decisions are based on the personality, experience, and skills of the applicants. Learn more here. </p>