AI Engineer Needed for LLM, RAG & AI Agent Development

We’re looking for an experienced AI/ML Engineer to help us build and deploy an AI-powered application using LLMs, RAG, AI agents, and workflow automation. The ideal freelancer should have hands-on experience building production-ready AI systems rather than only working on prototypes or notebooks. What You’ll Work On Build and improve LLM-powered applications and RAG pipelines Develop AI agents capable of calling APIs, processing information, and completing multi-step tasks Implement document ingestion, chunking, embeddings, vector search, re-ranking, and source citations Optimize prompts, structured outputs, tool/function calling, and AI response quality Integrate models such as OpenAI, Claude, Gemini, Llama, or other LLMs Build APIs and backend services using Python and FastAPI Work with vector databases such as Pinecone, Qdrant, Weaviate, ChromaDB, FAISS, or pgvector Dockerize and deploy the application to AWS, Azure, or GCP Implement testing, monitoring, logging, and performance/cost optimization Provide clean, documented, and maintainable code Required Skills Strong experience with: Python, LLMs, RAG, LangChain, LangGraph, Prompt Engineering, OpenAI API, Claude API, Vector Databases, FastAPI, Docker, Git, and AI Agent Development. Experience with MLOps, AWS, NLP, machine learning, and automation tools such as n8n is a strong plus. What We’re Looking For We need someone who can take an AI concept from architecture → working prototype → production deployment. You should be comfortable evaluating AI accuracy, identifying failure points, improving retrieval and prompts, and explaining technical decisions clearly. Please include examples of RAG applications, AI agents, LLM applications, or similar production AI projects you have built.