Home / Projects / LLM / RAG Engineer
LLM and RAG Engineer Projects

LLM / RAG Engineer

Projects focused on RAG, local and cloud LLM usage, Ollama, LangGraph, ChromaDB, prompt boundaries, context retrieval, vector memory, and contextual search.

Remote roles Python Backend systems

Professional focus

These projects show how RAG work depends on retrieval quality, permission boundaries, fallback behavior, and clear separation between generated text and deterministic system actions.

RAG LLMs Ollama LangGraph ChromaDB Embeddings Prompt design Context retrieval Vector memory Cloudflare Workers

Related projects

AI Kanban with RAG and agents using FastAPI

Internal platform with Python/FastAPI, React, WebSocket, RAG, vector memory, agents, and local LLMs for task orchestration and operational visibility.

Python FastAPI React