AI and Machine Learning developer based in Karnataka, India. I enjoy building intelligent systems that combine Computer Vision, Deep Learning, NLP, and Speech AI to solve real-world problems.

Currently exploring deep learning, computer vision, and multilingual AI systems through hands-on projects ranging from landslide detection using satellite imagery to question generation from multilingual text and speech.

Lately focused on model development, data-centric AI, and strengthening my foundations in algorithms, mathematics, and Japanese language learning.

Building — Computer Vision applications, image classification models, object detection systems, and AI-powered projects using Python.

Learning — Deep Learning architectures, CNNs, Transformers, Large Language Models (LLMs), MLOps fundamentals, and advanced Python.

Grinding — Data Structures & Algorithms, Machine Learning projects, and Japanese language practice.

Built an AI-powered landslide detection system using satellite imagery and deep learning to identify landslide-prone regions. Designed the complete pipeline from data preprocessing and augmentation to model training and evaluation, enabling automated terrain risk assessment from geospatial imagery.

Focused on improving classification performance across varying terrain conditions while handling challenges such as class imbalance and environmental variability.

Tech: Python, TensorFlow, Keras, OpenCV, NumPy, Pandas

Built an AI-powered question generation system capable of generating meaningful questions from both text and speech inputs across multiple languages. Designed a pipeline that combines speech processing, natural language understanding, and question generation to improve accessibility and automated learning workflows.

The system supports multilingual content, enabling users to provide either written text or spoken input and receive context-aware generated questions. Focused on preprocessing, language handling, and model optimization for diverse linguistic inputs.

Tech: Python, NLP, Deep Learning, Speech Processing, TensorFlow

Built a deep learning model to classify gender from facial images using Computer Vision techniques. Worked on image preprocessing, data augmentation, model training, and evaluation.

Tech: Python, TensorFlow, Keras, OpenCV

Implemented object detection pipelines using YOLO and OpenCV for real-time image analysis and recognition tasks.

Tech: Python, OpenCV, YOLO

Python • C++ • C

TensorFlow • Keras • PyTorch • Scikit-Learn

OpenCV • YOLO • CNNs • Image Processing

NumPy • Pandas • Matplotlib • Seaborn

MySQL • MongoDB

Git • GitHub • VS Code • Jupyter Notebook • Google Colab • Kagel Notebook

AI & Deep Learning — Neural Networks, Computer Vision, NLP, Transformers, RAG, and LLMs.

Computer Vision — Object Detection, Image Classification, Transfer Learning, and Model Optimization.

Japanese Learning — Preparing for JLPT N5 and building vocabulary daily.

Problem Solving — Practicing algorithms and coding challenges consistently.

📧 Email: sujankswork@gmail.com

💼 LinkedIn: sujan-k-s-a41261321

🐙 GitHub: https://github.com/Sujan-lab-cell

"Artificial Intelligence is the new electricity" 
                                                        -AI visionary Andrew Ng."*