I have practical experience of building machine learning models using a range of classical and neural network–based algorithms, with a focus on applying the right techniques. My deep learning work spans convolutional neural networks (CNN) for computer vision, recurrent and transformer-based architectures for NLP, and end-to-end predictive modeling for real-world applications.

Beyond modeling, have exposure of data engineering and system design aspects, including data ingestion, cleaning, feature engineering, and pipeline automation. I have experience designing scalable data workflows, integrating multiple data sources, and preparing data for production-grade machine learning systems.

I am actively involved in MLOps practices, including experiment tracking, versioning of data and models, CI/CD pipelines, containerization using Docker, and deploying models as APIs or applications. I have worked with cloud platforms to deploy, monitor, and maintain machine learning systems in production environments.

More recently, my focus has expanded to applied Generative AI, where I build LLM-powered applications using RAG pipelines, prompt engineering, and vector-based retrieval systems. Across all my work, I prioritize building practical, scalable solutions that translate raw data into reliable, real-world intelligence.