Full Stack Developer (RAG/LLM)

Jade Global; United States; Remote; USD 120,000 - 190,000; Full time

Job summary

Jade Global is seeking a Senior Full Stack Developer to build, deploy, and scale web applications powered by LLMs and RAG. You will own the end-to-end lifecycle from UI design to backend AI pipelines, delivering robust, responsive software.

You will architect frontend with React/Next.js and backend with Python FastAPI or Node.js, integrating vector databases and AI APIs while optimizing performance and reliability.

Qualifications

• 4+ years of full-stack software engineering experience with production RAG/LLM apps.
• Proficiency in JavaScript/TypeScript, React/Next.js, and modern UI libs.
• Strong Python (FastAPI) or Node.js backend and databases (PostgreSQL, MongoDB).
• Hands-on with LLM APIs (OpenAI, Anthropic), embeddings, semantic search.
• Experience with Docker, CI/CD, and cloud deployments (GitHub Actions, AWS/GCP, Vercel).

Responsibilities

• Full-Stack Feature Delivery: Architect and develop scalable web apps using React.js/Next.js for frontend and Python (FastAPI) or Node.js for backend.
• LLM & RAG Integration: Design RAG pipelines connecting data to LLMs via vector databases.
• AI Orchestration: Use LangChain, LlamaIndex, or LangGraph to build intelligent agents and prompt chains.
• API Development: Build and maintain secure RESTful APIs for AI model outputs and async interactions.
• Performance Optimization: Optimize vector searches, reduce LLM latency, implement caching/streaming for real-time features.

Skills

Full-stack development

JavaScript/TypeScript

React.js/Next.js

Python (FastAPI)

OpenAI / Anthropic APIs

Vector embeddings / semantic search

Docker / CI-CD / DevOps

Tools

PostgreSQL

MongoDB

Pinecone

Qdrant

pgvector

LangChain

LlamaIndex

LangGraph

Docker

GitHub Actions

Vercel

AWS/GCP

Job description

Role Overview We are seeking a Full Stack Developer to build, deploy, and scale web applications powered by Large Language Models (LLMs) and Retrieval-Augmented Generation (RAG). You will own the end-to-end development lifecycle, from designing responsive UIs to architecting robust backend AI pipelines.

Key Responsibilities

• Full-Stack Feature Delivery: Architect and develop scalable web applications using React.js/Next.js for the frontend and Python (FastAPI)/Node.js for the backend.
• LLM & RAG Integration: Design and implement RAG pipelines, connecting proprietary data to LLMs via vector databases (e.g., Pinecone, Qdrant, pgvector).
• AI Orchestration: Utilize frameworks like LangChain, LlamaIndex, or LangGraph to build intelligent agents and manage complex prompt chains.
• API Development: Build and maintain secure RESTful APIs to reliably serve AI model outputs and handle asynchronous user interactions.
• Performance Optimization: Optimize vector searches, reduce LLM response latency, and implement caching/streaming strategies for real-time generative features.

Required Qualifications

• Experience: 4+ years in full-stack software engineering, with actively building and deploying RAG/LLM applications in production.
• Frontend Mastery: Deep expertise in JavaScript/TypeScript, React.js, Next.js, and modern UI libraries (Tailwind CSS, Material UI).
• Backend & Infrastructure: Strong proficiency in Python (FastAPI) or Node.js, coupled with standard database management (PostgreSQL, MongoDB).
• AI/Data Stack: Proven hands-on experience with LLM APIs (OpenAI, Anthropic), open-source models (Hugging Face), vector embeddings, and semantic search.
• Cloud & DevOps: Familiarity with deploying containerized applications (Docker) and managing CI/CD pipelines via GitHub Actions, Vercel, or AWS/GCP.