Posts by Collection

portfolio

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

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

publications

Generating Frequently Asked Questions from Technical Support Tickets using Large Language Models

Published in SC ’25 Workshops of the International Conference for High Performance Computing, Networking, Storage and Analysis, 2025

Recommended citation: Joslin, C., Burns, D., Ashish, A., & Barezi, E. J. (2025, November). Generating Frequently Asked Questions from Technical Support Tickets using Large Language Models. Proceedings of the SC ’25 Workshops of the International Conference for High Performance Computing, Networking, Storage, and Analysis (pp. 715–726). Association for Computing Machinery.
Download Paper | Download Slides

talks

teaching

TDM: LLM-Powered Data Dashboard

Undergraduate and Graduate Course, Purdue University, The Data Mine; Caterpillar Inc, 2023

Corporate Partners Teaching Assistant

Introduction to PyTorch and Tensorflow

Workshop, Purdue University, Rosen Center for Advanced Computing, 2025

This introductory workshop presented the core concepts and workflows of PyTorch and TensorFlow, two widely used deep learning frameworks. Topics included tensors, computation graphs, automatic differentiation, gradient-based optimization, and the architectural and programming differences between the two frameworks.
Download Slides | Jupyter Notebook

Fine-Tuning and Compression of Large Language Models

Workshop, Purdue University, Rosen Center for Advanced Computing, 2026

This intermediate-level workshop introduced practical methods for fine-tuning and compressing large language models. Topics included full fine-tuning versus parameter-efficient fine-tuning, Low-Rank Adaptation (LoRA), QLoRA, key LoRA hyperparameters, model quantization, and GGUF conversion for local deployment.
Download Slides