I will build custom computer vision models

A
afnan_mustafij
A
afnan_mustafij
Afnan Mustafij

About this gig

I train computer vision models that work on your images, not just on benchmark datasets.

What I build:

  •  Image classification (defects, quality, products, plants)
  •  Object detection and counting (safety gear, retail, agriculture)
  •  Segmentation and OCR-style pipelines
  •  Models compressed to run on phones, Raspberry Pi and edge devices

Proof of depth: I compressed a 50M-parameter vision model to 11M parameters while keeping 98% of peak AUC (case study on theabm.dev).

You receive: Trained weights and clean PyTorch code · Evaluation report (precision, recall, mAP/AUC, confusion matrix, failure examples) · Inference script or small API + README.

Licensing: I default to permissively licensed models (RF-DETR, YOLOX, torchvision) so you can use the result commercially. Ultralytics YOLO is AGPL-3.0 I use it only if you hold its license or accept AGPL.

Honest limits: I train on a 16 GB GPU, so I fine-tune efficient architectures rather than pretrain huge ones.

Message me with your goal, sample images and how many labeled images you have.

Get to know Afnan Mustafij

Afnan Mustafij

Machine Learning Engineer

  • FromBangladesh
  • Member sinceJul 2026
  • Avg. response time1 hour
  • Languages

    English, Bengali
Software engineer in Dhaka, Bangladesh. I build modern, scalable products with a focus on AI and machine learning. I help turn half-working AI ideas into reliable features; RAG chatbots trained on your docs, custom computer vision models, clean web data extraction, or fixing AI-generated code so the app can actually ship. I care about clean architecture, solid engineering, and thoughtful UI. Lately focused on Edge AI and task-specific model fine-tuning so models perform well in real conditions. Happy to talk about what you’re building.