Sreelekshmi Saju User

AI and Machine Learning Engineer with a strong academic and practical background in Python, data analysis, statistical modeling, and applied machine learning. Experience in building, evaluating, and deploying machine learning and NLP solutions, including transformer-based architectures and large language models. Hands-on exposure to end-to-end ML workflows covering data preprocessing, feature engineering, model training, evaluation, and production deployment.

Applied deep learning techniques across computer vision and NLP tasks using CNNs, GANs, and transformer-based architectures. Improved model performance through data preprocessing, augmentation, and hyperparameter tuning, achieving 98.9% segmentation accuracy in medical image analysis and 92% classification accuracy in NLP-based sentiment analysis.

Enhanced model reliability by evaluating multiple machine learning and transformer-based models across balanced and imbalanced datasets. Used Accuracy, Precision, Recall, F1-Score, and Confusion Matrix metrics to guide model selection, resulting in consistent performance suitable for production deployment.

Streamlined end-to-end ML pipelines covering data preparation, feature engineering, model training, tuning, and deployment. Reduced overall development cycles by 40% while supporting real-time inference through deployed AI applications.

Primary interests include applied AI, deep learning, NLP, large language models, machine learning systems, explainable AI, and building scalable, data-driven solutions for real-world applications.