AI / LLM Engineer

Design and deploy production-grade LLM-powered systems using OpenAI, Anthropic, and open-source models (Llama, Mistral). Architect and build RAG pipelines with vector databases (Pinecone, Weaviate, pgvector) for enterprise knowledge retrieval. Build autonomous AI agents for workflow automation, customer support, and internal operations using LangChain / LlamaIndex. Implement robust prompt engineering, evaluation frameworks (RAGAS, DeepEval), guardrails, and content safety layers. Integrate LLM systems with enterprise APIs, CRMs, and data warehouses in secure, compliant environments