This project investigates the feasibility of running and fine-tuning lightweight Large Language Models (LLMs) on resource-constrained edge devices, specifically the NVIDIA Jetson platform. Our objective is to systematically evaluate multiple small-scale LLMs in terms of their inference accuracy, GPU memory usage, power consumption, and overall computational efficiency. By leveraging built-in monitoring tools and external measurement methods, we aim to provide a comprehensive comparison of model performance and resource demands. Following the evaluation phase, we fine-tune a selected model on a downstream task to assess how well Jetson handles on-device training or adaptation. This study highlights the trade-offs between model performance and hardware limitations, offering insights for real-world deployment of LLMs in low-power environments. The results will help guide model selection and optimization strategies for developers targeting edge AI applications with minimal computational overhead.

We’re Jobiter – a team of Hopkins students building an intelligent web platform to transform the job application process for college students and new graduates. By integrating AI-powered resume and cover letter optimization, application form auto-filling, and job recommendations based on individuals’ skills and qualifications, Jobiter streamlines the repetitive, time-consuming, and often demoralizing experience of navigating ATS (Applicant Tracking System) platforms.
Through powerful automation and customization, Jobiter dramatically boosts users’ chances of advancing past ATS filters and reaching the next stage of recruiting – the interviews.

An analysis of the 2024 NFL Kickoff Rule Change that focuses on the rule’s impact on the increased number of long field goal attempts in recent years

Developed in Dr. Lilian Josephson’s Product Design course, Liposol is a lecithin‑based liposomal sunscreen that leverages microfluidic assembly and rigorous ChemE modeling to deliver instant, uniform SPF 30 protection with minimal residue. Our team progressed from initial ideation to transport and thermodynamic analyses (Fick’s laws, microfluidic mixing, lipid self-assembly), designed a scalable manufacturing workflow (continuous‑flow microfluidics, tangential‑flow filtration), and built a 10‑year financial and business model forecasting breakeven in year 5 and robust market capture. Liposol exemplifies the seamless integration of chemical engineering principles, process development, and strategic planning to meet consumer demand for next‑generation, high‑performance sunscreen.