I will build machine learning and computer vision models with yolo and pytorch
Machine Learning Engineer, Computer Vision, OCR and AI Agents
About this Gig
I'm a Machine Learning Engineer working on production computer vision and edge AI. I'll train, optimize and deploy a model built on your own data.
Computer vision:
- Object detection and tracking (YOLOv8 / YOLO11, RT-DETR)
- Instance and semantic segmentation (YOLO-seg, SAM)
- Image classification and defect detection
- Dataset labeling, augmentation and training
Machine learning and NLP:
- Classification, regression and forecasting (scikit-learn, PyTorch, TensorFlow)
- Text classification and sentiment analysis with Transformers
Deployment: FastAPI, Docker, ONNX / TensorRT, NVIDIA Jetson and cloud (AWS).
What you get: trained model weights, clean training and inference code, an accuracy report (mAP, precision, recall) and a short demo video.
Send me sample images or data and what you want to achieve, and I'll suggest the right approach before you order.
My Portfolio
FAQ
I don't have a labeled dataset. Can you still help?
Yes. The Standard and Premium packages include image labeling. I can also start from a pretrained model or a public dataset to reduce how much data you need.
Can the model run on edge devices like Jetson or Raspberry Pi?
Yes. I optimize models with ONNX and TensorRT for real-time inference on NVIDIA Jetson and other edge hardware. This is included in the Premium package.
Do I get the trained model and source code?
Yes. You receive the trained weights, training and inference code, and a short guide so you can retrain or run the model yourself.
