Full Stack AI Engineer at Car Housing (AI/LLM feature delivery with RAG + LLM integration)
Built production LLM features by integrating OpenAI and Claude with RAG pipelines for context-aware generation. Implemented semantic retrieval workflows using vector databases to improve relevance and downstream generation quality. Supported AI-driven automation by designing prompts and generation logic for deployed services. • Integrated OpenAI and Claude for LLM responses • Implemented RAG with vector databases for semantic retrieval • Improved context-aware generation relevance (reported 70% relevance boost) • Deployed and operated LLM features in production microservices