I will build computer vision object detection, yolo

Pakistan

I speak English, Urdu

AI Engineer LLM, RAG Chatbots Computer Vision

AI Engineer with 1+ years production experience building LLM chatbots, RAG pipelines, and computer vision systems for clients in retail, FMCG, and banking. I turn messy data into deployed products — Y...
About this Gig

I build custom computer vision systems that automate visual tasks object detection, image classification, tracking, and OCR using YOLO, OpenCV, TensorFlow, and PyTorch.

In production, I've built CV pipelines for global brands (Samsung, L'Oréal) that automated manual visual review work and cut task time by 60%. I also led a real-time sign-language translation system (88% accuracy) with a full Flask-based interface.

What I can build:

  • Custom object detection/classification models (YOLOv8, TensorFlow, PyTorch)
  • Real-time video/webcam detection pipelines
  • Model training on your own labeled dataset (or I can help label it)
  • Simple web/app interface to demo or use the model
  • Model optimization for speed/accuracy tradeoffs

Tech stack: Python, YOLO, OpenCV, TensorFlow, Keras, PyTorch, Flask

Send me a sample of your images/videos and I'll tell you what accuracy and turnaround to expect.

APIs:

Microsoft Computer Vision AI

Amazon Rekognition

Expertise:

Image processing

Feature learning

Classification

Programming language:

Python

R

SQL

Colab

MLflow

Tools:

Jupyter Notebook

OpenCV

OpenNN

TensorFlow

MLflow

Colab

Frameworks:

Scikit-learn

DeepPy

Keras

PyTorch

Panda