
Principal AI Architect (f/m/d)
Volkswagen10 days ago
Wolfsburg, Germany +3 moreStaff+
Responsibilities
- Define the technical architecture and reference architectures for CARIAD’s R&D AI solution landscape, including model routing, context engineering, retrieval, agent orchestration, tool integration, evaluation, observability, APIs, and secure execution.
- Develop hands-on reference solutions and prototypes to validate architectural decisions through code, benchmarks, and concrete implementations.
- Establish reusable software components, technical standards, stable interfaces, and production-readiness criteria.
- Ensure AI systems meet quality, reliability, security, safety, privacy, scalability, performance, latency, observability, and cost-efficiency requirements.
- Conduct architecture and code reviews and support engineering teams with cross-team architectural challenges.
- Evaluate build, buy, and reuse options based on compatibility, integration effort, vendor dependencies, and total cost of ownership.
- Collaborate with domain engineers and decentralized AI teams to translate requirements into scalable, production-ready AI solutions.
- Integrate AI capabilities into existing R&D requirements, source-code, build, testing, and validation toolchains.
- Document architectural decisions, trade-offs, production-readiness criteria, and reusable engineering patterns.
Requirements
- University degree in Computer Science, Software Engineering, or a related field, or equivalent practical experience.
- Proven experience designing and developing complex distributed software systems and taking architectural responsibility across multiple teams.
- Hands-on experience developing and deploying production-grade AI applications, especially LLM-based solutions, RAG, and agentic systems.
- Strong Python programming skills and knowledge of API design, cloud-native architectures, distributed systems, and resilient software engineering.
- Deep understanding of agentic architectures, tool and function calling, agent orchestration, state and context management, human-in-the-loop approaches, and controlled execution.
- Experience evaluating LLM and agentic systems using test datasets, quality metrics, regression testing, LLM-as-a-Judge approaches, and quality, latency, and cost benchmarks.
- Experience integrating LLMs, multimodal models, and embedding models, including model-routing and abstraction mechanisms.
- Knowledge of context engineering, retrieval architectures, embeddings, vector search, reranking, prompt and context management, security, privacy, identity and access management, guardrails, and secure tool usage.
- Experience with AI-specific observability and tracing across models, agents, tool calls, retrieval, and end-to-end execution flows.
- Experience with Microsoft Azure and/or Databricks, including cloud infrastructure, identity and access management, observability, and CI/CD.
- Ability to review code and architecture, develop prototypes, and validate technical decisions through measurable implementation results.
- Deep hands-on experience with at least one modern GenAI or agentic AI technology stack and the ability to assess its architecture, limitations, and trade-offs.
- Strong analytical, problem-solving, communication, and cross-organizational collaboration skills, including excellent English.
Benefits
- Opportunity to work at CARIAD, Volkswagen Group’s automotive software company, on AI platforms and digital customer functions for brands including Audi, Volkswagen, and Porsche.
- Collaborate with teams across Germany, the USA, China, Estonia, and India.
- Inclusive and diverse work environment with application assistance available for candidates with disabilities.