You will get a computer vision system deployed on NVIDIA Jetson Nano, Orin, Thor
Project details
Need a real-time computer vision system running on NVIDIA Jetson? I handle everything from flashing your board to delivering a working system. Whether you need object detection, tracking, or any visual AI task at the edge, I can build it.
Here is what I can do for you:
- Flash and configure your Jetson (Nano, Orin, Thor) with the right JetPack, CUDA, and TensorRT versions
- Train a detection or classification model on your specific data
- Optimize with TensorRT so it runs fast on limited hardware
- Build the full inference pipeline with your camera or video source
- Package everything with clear setup instructions so your team can maintain it
I have worked with deep learning models (YOLOv8, YOLOv11, SAM, ResNet) and optimization techniques including FP16/INT8 quantization. If you already have a trained model, I can take it from there. If starting from scratch, I handle dataset preparation and training too.
Message me if you are unsure which tier fits your project. Happy to discuss before you order.
Here is what I can do for you:
- Flash and configure your Jetson (Nano, Orin, Thor) with the right JetPack, CUDA, and TensorRT versions
- Train a detection or classification model on your specific data
- Optimize with TensorRT so it runs fast on limited hardware
- Build the full inference pipeline with your camera or video source
- Package everything with clear setup instructions so your team can maintain it
I have worked with deep learning models (YOLOv8, YOLOv11, SAM, ResNet) and optimization techniques including FP16/INT8 quantization. If you already have a trained model, I can take it from there. If starting from scratch, I handle dataset preparation and training too.
Message me if you are unsure which tier fits your project. Happy to discuss before you order.
AI Development Type
Deep Learning, Model Tuning, Recommendation System, Software MaintenanceAI Tools
Amazon SageMaker, Azure Machine Learning, Keras, MATLAB, NVIDIA AI Platform, OpenCV, PyTorch, TensorFlowAI Development Language
C++What's included
| Service Tiers |
Starter
$250
|
Standard
$1,600
|
Advanced
$4,000
|
|---|---|---|---|
| Delivery Time | 2 days | 7 days | 30 days |
Number of Revisions | 1 | 1 | 1 |
AI Model Integration | - | ||
Detailed Code Comments | - | - | |
Knowledge Graph | - | - | - |
Model Documentation | - | ||
Ontology | - | - | - |
Source Code | - | - | |
Taxonomy | - | - | - |
Frequently asked questions
9 reviews
(8)
(1)
(0)
(0)
(0)
This project doesn't have any reviews.
IN
Ihor N.
Nov 2, 2025
Consultant Needed for Roboflow and YOLO Object Detection Training
RP
RJ P.
Apr 11, 2025
Machine learning tool for material identification
The project went smoothly and was delivered ahead of schedule.
YB
Yusuf B.
Nov 29, 2024
3D Reconstruction Pipeline
Great communication, skills stuck to the deadlines and offered great ideas to improve the project.
AL
Alex L.
Jul 8, 2024
Facial recognition to a web application that uses the camera and recognizes with AI skin problems.
Faruk is a great person, willing to help and solve the needs of what is needed, thanks for everything.
NR
Nils R.
Jul 5, 2024
AI/ML Prototype Developer for UKEY App
Faruk was a pleasure to work with, very skilled at what he does and Impeccable communication. I would be happy to work with him again
About Md Faruk
Computer Vision, Machine Learning, Jetson, C++ | AI Agent, Claude Code
78%
Job Success
Rangamati, Bangladesh - 3:26 pm local time
✅ What I Build
▸ Computer Vision: object detection, tracking, segmentation, pose estimation, image classification, counting, OCR, anomaly detection
▸ Edge AI: NVIDIA Jetson (Nano, Orin, Xavier), Raspberry Pi, model optimization with TensorRT, ONNX, and TFLite for real-time inference
▸ Image Generation: Stable Diffusion (SDXL, SD 3.5), Flux, DALL·E 3, ControlNet, LoRA fine-tuning, ComfyUI workflows
▸ Video Generation: Kling, Runway Gen-3, Minimax Hailuo, Veo, Pika, automated cinematic and product video pipelines
▸ AI Agents: autonomous multi-step agents using LangChain, LangGraph, CrewAI, and AutoGen with RAG, memory, and tool use
▸ Voice AI: conversational voice agents using Vapi, Retell AI, ElevenLabs, Bland AI, and Deepgram for inbound/outbound calling and automation
▸ MCP Servers: custom Model Context Protocol servers connecting Claude and other agents to your APIs, databases, and internal tools
▸ Claude Code: agentic software engineering with subagent architectures, skill-based pipelines, and autonomous multi-step coding workflows
✅ Tech Stack
▪ Computer Vision: OpenCV, YOLO, MediaPipe, Detectron2, SAM, Vision Transformers
▪ Deep Learning: PyTorch, TensorFlow, Keras, ONNX
▪ Tracking & Optimization: DeepSORT, ByteTrack, TensorRT, OpenVINO
▪ Deployment: DeepStream, Triton Inference Server, TFLite, FastAPI, Flask, Docker
▪ Generative AI: Stable Diffusion, Flux, ComfyUI, Replicate, Fal.ai
▪ Agents & Voice: LangChain, LangGraph, CrewAI, Vapi, Retell AI, ElevenLabs, n8n
▪ MCP & Agentic: Claude Code, MCP SDK, custom tool servers
▪ Cloud: AWS, GCP, Azure
▪ Languages: Python, C++, CUDA
🚀 Send me a message with what you are trying to build, and let's discuss.
Steps for completing your project
After purchasing the project, send requirements so Md Faruk can start the project.
Delivery time starts when Md Faruk receives requirements from you.
Md Faruk works on your project following the steps below.
Revisions may occur after the delivery date.
Set Up Jetson Environment
Flash device and install CUDA, TensorRT, JetPack, PyTorch.
Train or Optimize Model
Train custom model on your data or optimize your existing model with TensorRT.