Ameen A S (ANA)

Designed and deployed deep learning models achieving up to 96% accuracy for time series forecasting and image classification tasks. Developed real-time data pipelines using Kafka, Spark, and AWS S3 enabling scalable and low-latency streaming data processing. Containerized machine learning APIs with Docker and automated CI/CD workflows via GitHub Actions to ensure smooth deployment to AWS ECS. Engineered end-to-end ML workflows including data preprocessing, model training, evaluation, and deployment using Python, Scikit-learn, TensorFlow, and PyTorch. Automated data ingestion and transformation workflows using Apache Airflow and AWS Glue supporting batch and streaming ETL pipelines. Built and deployed Flask-based inference APIs integrated with cloud services for real-time model predictions and scalable service orchestration. Ensured secure, scalable deployments using AWS EC2, ECR, and IAM with Dockerized services monitored and managed in production environments. Collaborated closely wit

Developed and optimized machine learning pipelines for classification and regression tasks achieving up to 98% accuracy. Implemented Natural Language Processing techniques using spaCy, TensorFlow, and CountVectorizer for text data preprocessing and vectorization. Trained and evaluated machine learning models including Logistic Regression, Naive Bayes, XGBoost, and Random Forest with effective hyperparameter tuning. Engineered feature selection and extraction pipelines enhancing model performance and reducing dimensionality using PCA and correlation analysis. Built automated data preprocessing workflows for structured and unstructured data using Pandas, NumPy, and Scikit-learn Pipelines. Applied cross-validation and classification metrics ensuring robust model evaluation and prevention of overfitting. Visualized model performance and data distributions using Matplotlib and Seaborn, aiding stakeholder communication and model interpretability. Packaged and documented ML solutions for repr

Contributed to front-end and back-end components of educational tools focusing on scalability and performance. Participated in Agile sprint planning, testing, and deployment activities.