Full-Stack AI Engineer: Python, Langchain, RAG, Next.js, Django/FastAPI (Project for Amit Gupta)

Cliente Freelancer · Remoto · Remoto · freelance · mid · 30–250 USD

Publicada el 2026-07-23

Descripción de la oferta

We are seeking an expert Full-Stack AI Engineer to architect and build a scalable, proprietary AI application from the ground up. You will be responsible for developing a highly responsive Next.js frontend integrated with a high-performance Python backend (FastAPI preferred for async/streaming, or Django). The core of this product relies on a custom Retrieval-Augmented Generation (RAG) system built with Langchain to securely and intelligently query complex datasets. If you have a proven track record of bridging advanced AI data pipelines with production-ready APIs and intuitive UI/UX, we want to hear from you. Required Technical Skills Frontend: Next.js, React, and modern UI frameworks (Tailwind CSS, etc.). Backend: Python, FastAPI or Django/DRF, PostgreSQL. Async & Streaming: Experience with Celery/Redis for background tasks and Server-Sent Events (SSE) or WebSockets for streaming LLM responses. AI/LLM Frameworks: Langchain, LlamaIndex, and commercial/open-source LLM integration. RAG & Data Architecture: Vector Databases (pgvector, Pinecone, ChromaDB, Qdrant), custom embedding generation, and advanced document chunking strategies. DevOps: Docker, AWS/GCP/Azure, and Vercel deployment. Deliverables & Milestones Milestone 1 (Scoping & Technical Architecture): Deliver a comprehensive technical specification detailing the database schema, API design, RAG architecture, and deployment strategy to get started. Milestone 2 (Backend & AI Core): Set up the FastAPI/Django backend, configure the vector database, process initial data, and build the Langchain RAG API endpoints. Milestone 3 (Frontend & MVP): Build the Next.js frontend, connect the backend APIs (ensuring smooth token streaming for LLM responses), and deliver a functional end-to-end prototype. Milestone 4 (Optimization & Deployment): Optimize retrieval latency, stress-test the RAG system to minimize hallucinations, refine the UI, and deploy to a production environment.

Skills

• RAG
• JavaScript
• Next.js
• FastAPI
• LangChain
• Python
• Django
• Vector Databases
• PostgreSQL
• AWS
• Tailwind CSS
• Docker
• UI/UX Design
• React
• Azure
• Google Cloud
• WebSocket
• LlamaIndex
• pgvector
• Vercel

Fuente original: freelancer