You will get Build LLM-Based AI Multi-Agent System (Python / LangChain/ n8n / CrewAI)
Project details
I specialize in building LLM-powered multi-agent systems where multiple AI agents collaborate to solve complex tasks. What sets this project apart is the end-to-end approach: not just creating basic chatbots, but designing a scalable, production-ready ecosystem tailored to your business needs.
With expertise in Python, LangChain, CrewAI, and n8n. I deliver systems with:
Intelligent agent collaboration
API & data source integration
Optimized performance with prompt engineering, caching, and orchestration
Deployment-ready solutions
Example Projects
Trip Planning Assistant – Researches destinations, compares flights/hotels, builds itineraries, and optimizes budgets.
Market Research Agent – Gathers resources, summarizes trends, and creates competitor comparison reports.
Customer Support Automation – Multi-step ticket handling, categorizes, drafts a response, and verifies accuracy.
Content Generation Workflow – Research, write drafts, polish, and publish on blogs/social media.
Financial Data Monitoring.
Whether you need a proof-of-concept, a workflow automation assistant, or a full-scale AI agent platform, I’ll ensure your system is reliable, scalable, and aligned with your goals.
With expertise in Python, LangChain, CrewAI, and n8n. I deliver systems with:
Intelligent agent collaboration
API & data source integration
Optimized performance with prompt engineering, caching, and orchestration
Deployment-ready solutions
Example Projects
Trip Planning Assistant – Researches destinations, compares flights/hotels, builds itineraries, and optimizes budgets.
Market Research Agent – Gathers resources, summarizes trends, and creates competitor comparison reports.
Customer Support Automation – Multi-step ticket handling, categorizes, drafts a response, and verifies accuracy.
Content Generation Workflow – Research, write drafts, polish, and publish on blogs/social media.
Financial Data Monitoring.
Whether you need a proof-of-concept, a workflow automation assistant, or a full-scale AI agent platform, I’ll ensure your system is reliable, scalable, and aligned with your goals.
AI Algorithms
Large Language Model, Long Short-Term Memory Network, Transformer Model, Variational AutoencoderAI Applications
AI Chatbot, AI Content Creation, AI Mobile App Development, AI Text-to-Image, AI Text-to-Speech, AI-Enhanced Classification, AI-Generated Art, AI-Generated Code, AI-Generated Video, Automatic Speech Recognition, Image Recognition, Speech SynthesisAI Development Language
PythonAI Tools
Azure OpenAI, GitHub Copilot, Hugging Face, NVIDIA AI Platform, PyTorch, TensorFlowAI Models
BERT, ChatGPT, DALL-E, GPT-3, GPT-4, GPT-Neo, LaMDA, LLaMA, Midjourney AI, OpenAI Codex, Stable Diffusion, WhisperWhat's included
| Service Tiers |
Starter
$300
|
Standard
$800
|
Advanced
$2,500
|
|---|---|---|---|
| Delivery Time | 3 days | 6 days | 14 days |
Number of Revisions | 2 | 4 | 8 |
AI Model Integration | - | ||
Batch Normalization | - | - | - |
Database Integration | - | - | |
Detailed Code Comments | |||
Image Upscaling | - | - | - |
MLOps | - | - | - |
Model Deployment | - | - | - |
Model Documentation | - | - | |
Model Monitoring | - | - | - |
Model Testing & Optimization | - | - | - |
Model Tuning | - | - | - |
Natural Language Processing | - | - | - |
NLP Tokenization | - | - | - |
Pre-Training | - | - | - |
Prompt Engineering | |||
Setup File | - | - | - |
Source Code |
About Yasiru
Computer Vision & AI Agent Engineer | YOLO, Tracking, Multi-Agent LLM
Galle, Sri Lanka - 7:21 pm local time
I specialize in Computer Vision, real-time video analytics, and intelligent AI systems with hands-on experience developing solutions that detect, track, analyze, and understand visual data.
🧠 Computer Vision My Core Expertise
I build custom Computer Vision systems for applications such as:
• Object detection & classification using YOLO
• Multi-object tracking and real-time tracking systems
• Real-time video analytics and CCTV analysis
• AI-powered camera systems
• Player & ball tracking for sports analytics
• OCR and document/image understanding
• Number plate / license plate recognition
• Retail, traffic, security, and industrial vision systems
• Edge AI deployment on NVIDIA Jetson and Raspberry Pi
• GPU-accelerated inference and performance optimization
I work with technologies including Python, OpenCV, PyTorch, TensorFlow, YOLO, ONNX, CUDA, GStreamer, FastAPI, and real-time streaming technologies.
I've worked on systems involving multiple cameras, RTSP video streams, GPU inference, object tracking, model optimization, and edge-device deployment going beyond a simple AI demo or notebook.
🤖 LLM & Multi-Agent Systems
I also build intelligent LLM-based systems that can reason, use tools, interact with external services, and automate complex workflows.
My experience includes:
• Multi-agent AI systems
• LLM workflow automation
• AI agents using LangGraph / CrewAI and similar frameworks
• n8n-based AI automation
• RAG and knowledge-based AI systems
• Tool-using AI agents
• MCP-based integrations
• OpenAI, Gemini, Claude and other LLM integrations
• Business process automation using AI agents
I focus on building reliable systems that can actually be integrated into real business workflows rather than simple chatbot demos.
🚀 What I Can Build
Whether you need a Computer Vision model, a real-time AI video pipeline, an OCR system, an AI camera, or a multi-agent automation system, I can handle the development from concept to deployment.
Typical projects include:
→ Custom YOLO object detection & tracking
→ Real-time video analytics
→ AI CCTV / security analytics
→ Sports Computer Vision systems
→ OCR & document intelligence
→ License plate recognition
→ AI camera and edge AI systems
→ GPU-optimized inference pipelines
→ LLM multi-agent applications
→ AI workflow automation
→ RAG and knowledge-based AI systems
→ API/backend integration for AI systems
⚙️ My Approach
I don't just train a model and hand over a notebook.
I can work across the full AI development lifecycle:
Problem → Data → Model → Inference → Optimization → API → Deployment
This includes model development, backend integration, real-time processing, GPU optimization, streaming pipelines, and deployment when required.
I’m particularly interested in challenging projects where Computer Vision, real-time systems, edge AI, and modern LLM technologies need to work together.
🎓 Background
I hold a Bachelor's degree in Computer Science from the University of Moratuwa and have spent 6+ years working with AI and software engineering.
If you have a Computer Vision, AI, or LLM-agent project and need an engineer who can take it from an idea or prototype toward a reliable working system, feel free to message me with the details.
I’m happy to discuss the technical requirements and suggest the most practical approach.
Steps for completing your project
After purchasing the project, send requirements so Yasiru can start the project.
Delivery time starts when Yasiru receives requirements from you.
Yasiru works on your project following the steps below.
Revisions may occur after the delivery date.
Discovery & Requirements
Gather goals, success criteria, must-have features, constraints (security, data residency, cost caps), and example tasks. Deliverable: Requirements summary + prioritized feature list and acceptance criteria.
High-level Architecture & Tech Selection
Propose an architecture (agents, orchestrator, vector DB, hosting, monitoring) and pick the tech stack (LangChain/CrewAI, OpenAI/Llama API, Pinecone/FAISS, FastAPI, n8n, etc.). Deliverable: Architecture diagram and tech stack decision document.