I will create llm or multimodal ai chatbot


Level 2
About this gig
Hi,
I am a Senior Software Engineer and Full-stack AI Product Architect with 6 years in software development and 3 years in AI agents. My expertise spans end-to-end AI system architecture, autonomous AI agents and multi agent system, AI finetuning, and custom AI model deployment, enabling businesses to deploy scalable and impactful AI solutions.
What I can build for you:
- Text: real-time chat, content generation, Q&A, web search
- Audio: real-time TTS/STT voice assistants
- Vision: image generation, editing pipelines, Lora
- Video: video generation with Veo3 and WAN2.2, editing workflows, AI-driven animation
- Code & automation: code generation AI agents, react coding agents, MCP agents, langchain agents
- Advanced agentic system: autonomous agents, multi-agent systems, data extraction, document chat, interactive storytelling, browser control agents, voice calling agents, RAG agents
Tools & Frameworks I use
- AI/ML frameworks: LangChain, LlamaIndex, Llama.cpp, MCP
- Tools: ComfyUI for image pipelines, RunPod for scalable serverless GPU deployment
- Cloud providers: Azure, AWS, GCP
- Vector DB: PostgreSQL, ChromaDB, MongoDB
Platforms I can develop apps for: web, desktop, mobile
Get to know Ellis S
Senior Software Developer, AI Product Engineer, Entrepreneur
Level 2
- FromChina
- Member sinceMar 2022
- Avg. response time1 hour
- Last delivery1 month
Languages
English, Chinese
My Portfolio
FAQ
What types of agents can you develop?
I can develop agents using various models (such as LLM, TTS/STT, Image Gen, Video Gen, Music Gen) and tools (such as Python, Zapier, Make, Pulse Editor).
Will I need coding skills to use the agent?
I can deliver user-friendly agents that you can run without technical knowledge. Additional fees apply for UI/UX frontend development.
Can you maintain or update the agent after delivery?
Yes, I offer ongoing support and updates upon request to keep your agent running smoothly at a discounted rate.
