I build systems that generate, understand, and speak — from RAG pipelines and fine-tuned transformers to voice assistants that listen back. CS undergrad at SRM University, Tiruchirappalli.
A Computer Science undergraduate specializing in AI & Machine Learning, focused on bridging complex generative models with practical, user-centric applications.
My work spans Retrieval-Augmented Generation, large language models, and voice-driven interfaces — built and deployed using Watsonx, OpenAI APIs, LangChain, and NLP models for real tasks like voice translation, emotion detection, and automated image captioning. I care about writing clean, modular Python and keep exploring state-of-the-art transformer architectures. Currently open to AI/ML engineering, generative AI development, and software engineering roles.
A neural translation system converting text across languages using transformer-based sequence models.
A generative model composing original musical sequences, exploring creativity in generative architectures.
A computer vision pipeline that detects and localizes objects in images in real time.
An automated captioning system pairing a vision encoder with a language decoder to describe images.
A chatbot that translates whatever message you send it, powered by an LLM with dynamic language detection.
A custom voice assistant app combining speech-to-text and text-to-speech for natural spoken interaction.
A 16-course series covering the full generative AI engineering stack — from foundations to applied LLM and RAG systems.
Practical data analysis training covering querying, spreadsheet modeling, and business intelligence dashboards.