PromptBeaver
Published:
Created a Streamlit prompt-engineering tool that helps students build, evaluate, and refine prompts for large language models through guided prompt analysis rather than direct answer generation.
Source Code
Portfolio
CLiFF (Clustering & Language model integration for FAQ Formation)
Published:
Constructed CLiFF, a natural language processing pipeline that uses a fine-tuned large language model and semantic clustering to transform recurring technical support issues into frequently asked questions.
Source Code
ML Job Compass
Published:
Built a Streamlit application that analyzes 1,000+ machine learning job postings using natural language processing and retrieval-augmented generation to identify in-demand skills and generate personalized learning roadmaps. Manuscript submitted for publication.
Source Code
Dog and Cat Breed Classifier
Published:
Trained a MobileNetV2 transfer-learning model to classify 104 dog and cat breeds from 29,000 images, achieving an 84% F1 score.
Source Code