Browse categories
Explore
Fiverr Pro
English
$
USD
I will build ai chatbot using llm, rag and vector database
zhumingming
About this gig
Hi! I'm a full-stack developer specializing in AI chatbots and LLM integration, with 3+ years of experience.
I built my own machine learning platform (njmaet) and deployed 35B-parameter MoE models on 8-GPU servers for enterprise clients. I know AI systems end-to-end: from model selection to production deployment.
WHAT I BUILD FOR YOU:
1. AI Chatbots GPT, Claude, or open-source models (Llama, Qwen, DeepSeek) integrated into your website or app
2. RAG Chatbots a chatbot that answers from YOUR documents (PDF, website, database) using vector search (Milvus, Faiss)
3. Custom AI Assistants fine-tuned on your data, speaking in your brand's voice
WHY WORK WITH ME:
- Real production experience: I deploy LLMs (7B-70B) on GPU servers using vLLM and Ollama
- Full-stack: your chatbot gets a clean web interface (Node.js + React), not just a script
- I handle APIs, databases, deployment, and documentation
- Clear communication, on-time delivery
HOW IT WORKS:
1. Send me a message describing your project
2. I reply with a plan, timeline, and the right package for you
3. You get progress updates until delivery
Have questions? Messag
Get to know zhumingming
zhumingming
Full Stack Developer and AI LLM Deployment Specialist
- FromChina
- Member sinceOct 2026
- Avg. response time1 hour
Languages
Chinese, English
Full-stack developer, 3+ years in web dev and AI/ML deployment.
• Full-Stack: Node.js + React, PostgreSQL/MongoDB, APIs, dashboards
• AI Deployment: LLMs (7B-70B) on GPU servers via vLLM, Ollama
• Fine-tuning: QLoRA/LoRA on custom datasets
• AI Integration: RAG, vector DBs (Milvus/Faiss), chatbots, MCP connectors
Built a dedicated ML platform (njmaet) from scratch, and deployed 35B MoE models on 8-GPU servers for enterprise clients. From training to production — I handle it all.
Reliable, on time. Let's discuss your project!
FAQ
What do you need from me to start?
Just a description of your project: what the chatbot should do, where it will be used (website, app), and any documents or data you want it to answer from. I'll guide you through the rest.
Can the chatbot answer questions about my own documents?
Yes! That's exactly what RAG does. I connect your PDFs, website content, or database to the chatbot, so it answers from YOUR data with accurate, relevant responses.
Do you use OpenAI GPT or open-source models?
Both. I can use OpenAI GPT or Claude, or open-source models (Llama, Qwen, DeepSeek) if you want no API costs or private deployment on your own server.
Do I need my own API key or server?
For GPT-based chatbots, you'll need an OpenAI API key (I'll show you how). For open-source models, I can deploy on your server or recommend the cheapest hosting option.
Do you offer support after delivery?
Yes — Premium package includes documentation and a support period. Small fixes are always free. For long-term maintenance, message me for a custom offer.
