AI Engineering

Practical integration of large language models (LLM: OpenAI, Anthropic Claude, open-source Llama/Mistral models) into existing business processes. Building RAG (Retrieval-Augmented Generation) systems based on vector databases (Qdrant, Pinecone, pgvector) for smart search across a company's internal documentation. Development of AI agents on LangChain / LlamaIndex, configuration of function calling, prompt engineering, validation and structuring of model responses via JSON/Pydantic schemas.