I'm an Artificial Intelligence Engineer specializing in Computer Vision and Machine Learning, with over 6 years of experience developing innovative solutions for real-world applications. My expertise includes object detection, tracking, Retrieval-Augmented Generation (RAG), image preprocessing, and building optimized, real-time applications using multiprocessing and edge computing. I have extensive experience with Python, deploying AI models efficiently on platforms like Jetson devices, and optimizing video processing pipelines using GStreamer. Additionally, I'm proficient in using Docker for containerization, enabling seamless deployment and scalability. My passion lies in solving complex challenges and improving performance to deliver impactful and user-centric solutions.

• 🚀 Computer Vision & Deep Learning

  • Real-time object detection using YOLO.
  • Model optimization and conversion (PyTorch → ONNX → TensorRT).
  • Custom model training and fine-tuning for specific applications.
  • Image classification and segmentation.
  • Advanced techniques including image preprocessing and augmentation.
  • Integration of AI models with edge devices (e.g., NVIDIA Jetson).

• 🎯 Tracking and Video Processing

  • RTSP streaming, optimized video pipelines, and real-time tracking.
  • Efficient implementation with threads, multiprocessing, and edge AI deployment.
  • Integration with GStreamer for video processing.

• 📖 Retrieval-Augmented Generation (RAG)

  • Intelligent systems leveraging OCR and document-based retrieval methods.
  • Tailored solutions for technical and industrial documentation.

• ⚙️ Image Preprocessing & Optimization

  • Enhancing video/image frames for improved detection accuracy.
  • Hardware optimization including camera selection, resolution, lenses, and illumination setups.

Feel free to connect with me on

💻 I'm always open to exciting collaborations, freelance opportunities, and projects focused on Computer Vision, AI, and Python development.