• Drive the architecture, development and optimization of (generative) AI applications with a strong focus on
model evaluation, retrieval-augmented generation (RAG), and prompt engineering.
• Implement end-to-end RAG pipelines (ingestion, chunking, embeddings, retrieval, re-ranking) and integrate them
with internal data sources.
• Design and integrate data storage for AI applications using vector search in Snowflake and relational databases
such as PostgreSQL.
• Analyze and integrate data from various sources, ensuring high data quality and preparing it for effective AIdriven solutions.
• Experiment with LLM models (e.g. OpenAI, Anthropic, Azure OpenAI) to improve performance, reliability and
applicability across business use cases.
• Establish and maintain robust engineering practices for GenAI applications (testing, observability, security,
performance optimization).
• Collaborate closely with our AI platform team to enhance, standardize and scale AI-driven capabilities across the
BMW Group.
• Work closely with different business units, helping them leverage AI models for real-world applications and
continuous improvements.
• Share your expertise in Generative AI, LLM orchestration, and software engineering with other teams,
contributing to knowledge-sharing and innovation within the organization.