About Me
Data professional with experience across Data Science, Machine Learning, Deep Learning, NLP, Generative AI, and Business Intelligence. Skilled in Python, SQL, and Power BI, with hands-on exposure to the full analytics li…
Data professional with experience across Data Science, Machine Learning, Deep Learning, NLP, Generative AI, and Business Intelligence. Skilled in Python, SQL, and Power BI, with hands-on exposure to the full analytics lifecycle: data cleaning, EDA, feature engineering, model development, evaluation, and visualization. Built SQL-based reporting systems, Power BI dashboards, PySpark workflows, and BERT/Transformer-based NLP solutions including sentiment analysis and semantic resume screening. Strong at translating complex technical concepts into practical, business-relevant solutions.
Experience
Data Science Instructor
<p>Deliver hands-on training in Python, Machine Learning, Deep Learning, NLP, SQL, and Power BI for real-world applications.</p><p> Guide learners through end-to-end workflows: data cleaning, EDA, feature engineering, model building, evaluation, and visualization using Pandas, NumPy, and Scikit-learn.</p><p> Build interactive Power BI dashboards and DAX measures to analyze KPIs and present data-driven insights.</p><p> Design real-world projects and assignments; conduct technical assessments, project reviews, and mock interviews.</p>
PROJECTS
Document Intelligence Chatbot using RAG and LLMs
<p>Project Name: Document Intelligence Chatbot using RAG and LLMs</p><p>I developed a Document Intelligence Chatbot that allows users to upload documents and ask questions based on their content. The system uses Retrieval-Augmented Generation (RAG), LangChain, embeddings, a vector database, and a Large Language Model (LLM) to generate relevant answers from the uploaded documents.</p><p>First, the documents are divided into smaller chunks. Embeddings are generated for these chunks and stored in a vector database. When a user asks a question, the system converts the question into an embedding, retrieves the most relevant document chunks using similarity search, and passes the retrieved context to the LLM to generate an accurate, context-based response.</p><p>Technologies Used: Python, Generative AI, LLMs, RAG, embeddings, LangChain, vector databases, and Streamlit.</p><p>Outcome: The chatbot helps users search and understand documents conversationally, reducing the need to read lengthy documents manually.</p>