Ai Intern
Summary
Gaining hands-on experience in Artificial Intelligence by working with state-of-the-art Large Language Models (LLMs). Developing innovative AI projects that solve real-world problems using modern ML/NLP techniques Exploring LangChain, Hugging Face Transformers, and Retrieval-Augmented Generation (RAG) to build intelligent AI applications.
Java, Python, C.
NumPy, Pandas, Streamlit, scikit-learn, Matplotlib, Data Analysis, Feature Engineering.
Tensor Flow, Lang Chain.
SQL, Data Science, Deep Learning, Natural Language Processing, Artifical Intelligence, LLM.
Summary
Built a predictive model for estimating mobile phone costs and improving cost estimation accuracy. Performed data preprocessing, feature selection, and model evaluation to ensure high prediction reliability. Evaluated model performance using cross-validation and fine-tuned hyperparameters.
Summary
Built an AI-powered tool to extract and answer questions from financial news and equity reports. Utilized LangChain, Hugging Face Transformers, and RAG to create a robust retrieval-augmented pipeline. Implemented chunking, embedding, and vector search for efficient document indexing and retrieval. Enabled users to input URLs and receive real-time insights from document content using LLMs.
Summary
Developed an app that scrapes job descriptions from career pages and generates personalized cold emails. Implemented a LangChain-based pipeline using LLaMA 3.1 and Retrieval-Augmented Generation (RAG) to extract job roles in structured JSON format. Delivered a one-click email generation workflow powered by FAISS, Hugging Face Transformers.
Summary
Built a Streamlit-based app that matches users with ideal profiles using natural language descriptions and persona-based preferences. Leveraged Sentence Transformers and FAISS to generate embeddings and perform efficient similarity searches for personalized results.