Principal Engineer - RAG Database & Embeddings Architect

What you'll do

• Design and govern vector databases, document and metadata stores, and hybrid retrieval architecture; define embedding and vectorization strategies.
• Lead retrieval quality, performance, observability, testing, and platform evaluation across enterprise AI teams.
• Set reusable architecture standards and provide technical leadership, design reviews, and mentoring across teams.

What they ask for

• 10+ years of software, data, platform, or AI engineering experience; 5+ years designing large-scale enterprise systems; 2+ years working with LLM, RAG, vector search, semantic search, or AI platform capabilities.
• Experience operating systems in regulated, security-conscious, or enterprise-scale environments and designing production-grade search, indexing, or database systems.
• Strong understanding of vector databases, embeddings, similarity search, approximate nearest neighbor algorithms, retrieval optimization, and RAG architectures.
• Bachelor’s degree in Computer Science, Engineering, Information Systems, Applied Mathematics, or a related technical field.

Nice to have

• Experience with hybrid retrieval, reranking models, knowledge graphs, or entity-aware retrieval.
• Experience with LLM and retrieval evaluation, automated relevance testing, model or embedding drift, and re-indexing strategies.

Tools

Azure AI Search, Cosmos DB vector search, Pinecone, Weaviate, Milvus, OpenSearch, Elasticsearch, PostgreSQL/pgvector

AI focus

Architects enterprise RAG and retrieval systems, including embedding strategies, vectorization, semantic and hybrid retrieval, relevance tuning, and retrieval-quality monitoring for LLM applications.