I'm a Machine Learning Engineer with a strong foundation in deep learning, big data, and scalable AI systems. With a passion for solving real-world problems, I specialize in building and deploying end-to-end machine learning solutions.
- Design, develop, and deploy ML models for production
- Build robust data pipelines using Python, Spark, and AWS
- Research and experiment with foundation models, NLP, computer vision, and LLMs
- Communicate complex insights through visualization and storytelling
- Languages & Frameworks: Python, PyTorch, TensorFlow, Scikit-learn, Spark, SQL
- Domains: Machine Learning, Deep Learning, NLP, Computer Vision, Anomaly Detection
- Platforms: AWS (Sagemaker, Glue, Batch), GitHub, Docker, Tableau, RedShift
As part of the University of Toronto DSI Certificate capstone team project, I co-developed this ML pipeline to classify skin conditions using different ML algorithms.
✅ My contributions (in collaboration with my teammates):
- Designed and trained tree models (XG Boost, Extra Trees, Random Forest), KNN, Naive Bayes, and SVM.
- Conducted exploratory data analysis and augmentation
- Built reusable training pipelines and evaluation scripts
- Delivered interpretable insights and presentation materials
A hands-on exploration of text generation using transformer-based architectures.
✅ Covers tokenizer engineering, fine-tuning, and GPT model behavior.
A repository of deep learning examples including CNNs, RNNs, and attention-based models built from scratch and with PyTorch/Keras.
- 🌐 Personal website coming soon!
- 📬 Email: [hossein.khonsari@gmail.com]
Thanks for visiting my GitHub! Feel free to explore, fork, or reach out if you'd like to collaborate.