Researcher in Machine Learning & Generative AI | Exploring LLMs, RAG Systems, and Scalable AI Pipelines
I’m a Machine Learning & Generative AI Engineer with an academic foundation in M.Tech (Applied Artificial Intelligence) and hands-on experience in building real-world AI systems.
At my core, I enjoy asking research-driven questions and then bridging them with practical engineering.
- During my M.Tech, I explored advanced algorithms, optimization, and deep learning architectures.
- In industry and personal projects, I’ve applied those foundations to build end-to-end ML pipelines, vector search systems, and RAG-based GenAI applications.
Beyond projects, I actively share knowledge through my #90DaysOfAI series on LinkedIn, where I break down complex AI concepts into accessible insights. This reflects not only my curiosity to learn but also my passion to contribute to the AI community.
Currently, I’m diving deep into:
- Generative AI – building with LLMs, LangChain, RAG pipelines, and fine-tuning models.
- Vector Databases – Milvus, Pinecone, Weaviate, FAISS for retrieval-augmented generation (RAG).
- AI Deployment – containerization with Docker & Kubernetes, scaling on AWS/GCP/Vertex AI.
- Full-Stack AI Apps – blending Python, FastAPI, and React for production-ready solutions.
Here’s the stack I use to transform raw ideas into intelligent solutions 👇
When I’m not experimenting with AI systems, you’ll find me writing about tech, mentoring peers, and storytelling through data.