a
akhellad

Djalil K

@akhellad

Computer Vision Engineer

França
Francês, Inglês
Algumas informações são exibidas no idioma inglês.
Sobre mim
Hi, I’m Djalil! I am a Machine Learning Engineer with over 5 years of experience specializing in Computer Vision and Deep Learning. I help businesses and startups build custom AI solutions that turn visual data into actionable insights. What I do: Custom Object Detection (YOLO expert) Image Segmentation & Tracking End-to-end AI Pipeline development Python & PyTorch integration My goal is to deliver high-quality, production-ready code tailored to your specific needs. Ready to unlock the power of AI? Send me a message, and let’s discuss your project!... Saiba mais

Habilidades

a
akhellad
Djalil K
offline • 
Tempo médio de resposta: 1 hora

Conheça meus serviços

Visão Computacional
I will help you build a custom computer vision solution
A partir deUS$ 90 /projetoMais detalhes
Limpeza de Dados
I will fix and convert your CV dataset for yolo, coco or roboflow
A partir deUS$ 15 /projetoMais detalhes

Portfólio

Experiência profissional

Fiverr

Computer Vision Engineer

Fiverr • Freelance

Feb 2026 - Present • 3 mos

As a dedicated Computer Vision Specialist with a Master’s degree in Data Science, I provide end-to-end AI solutions for global clients. My work focuses on bridging the gap between raw data and actionable insights through state-of-the-art Deep Learning techniques. Key Responsibilities & Achievements: Custom Model Development: Designing and training high-performance models using YOLO, PyTorch, and TensorFlow for real-time object detection and semantic segmentation. Data Engineering: Managing complex datasets, including high-precision manual annotation (Label Studio, CVAT) and data augmentation to improve model robustness. Optimization: Fine-tuning hyperparameters and implementing transfer learning to achieve 95%+ mAP on specialized datasets (Medical, Industrial, and Surveillance). Technical Consulting: Advising clients on the best architectural choices (U-Net, Mask R-CNN, EfficientNet) based on their specific hardware and accuracy requirements. Tools used: Python, PyTorch, OpenCV, Scikit-learn, Docker, and various Cloud AI platforms.