Debjit Roy

I am a motivated and innovative Computer Science undergraduate specializing in Artificial Intelligence and Machine Learning, with strong hands-on experience in building end-to-end AI and data-driven systems. My core strengths lie in Machine Learning, Deep Learning, and Generative AI, with a solid foundation in both theoretical concepts and practical implementation. I have extensive experience working with Python and modern ML frameworks such as TensorFlow, PyTorch, and Scikit-learn, enabling me to design, train, evaluate, and optimize predictive models for real-world problems. I have worked on LLM-based applications, including Retrieval-Augmented Generation (RAG) pipelines, semantic search systems, and vector database integrations, focusing on performance, scalability, and accuracy. My experience includes building intelligent systems using LangChain, Hugging Face, and vector search techniques to enable contextual and knowledge-aware AI solutions. In addition to NLP and Generative AI, I have a strong background in Computer Vision, where I have developed and experimented with YOLO-based object detection systems, U-Net architectures for image segmentation, and real-time vision pipelines. These projects strengthened my understanding of deep learning architectures, data preprocessing, and performance optimization in production-like environments. I am also skilled in data analysis, feature engineering, model evaluation, and hyperparameter tuning, ensuring robust and reliable machine learning pipelines. Alongside AI development, I have experience with scalable backend architectures, cloud computing concepts, and clean coding practices, allowing me to build systems that are both efficient and maintainable. I am a strong problem-solver with a keen interest in system optimization and continuous learning. I actively seek opportunities to apply my skills to impactful real-world challenges and contribute to innovative, technology-driven teams.