Reeyan Choudhury
Computer systems engineering
Hometown: Chandler, Arizona, United States
Graduation date: Spring 2028
Additional details: Honors student
FURI | Spring 2025
Reducing LLM Energy Waste via Automated Prompt Optimization
Large language models (LLMs) consume vast amounts of power, which has a significant impact on the environment through carbon emissions to generate the requisite power and water consumption to cool down the data centers used. This project uses a man-in-the-middle LLM to optimize a user’s request for quality short responses. This solution, depending on the request type, can significantly reduce output length, which is directly proportional to power consumption, reducing both environmental impact and cost while still maintaining user satisfaction. This solution creates a real incentive for companies to reduce environmental impact because it reduces cost.
Mentor: Adwith Malpe, Ryan Meuth
It’s hip to be square.
Students presenting projects at the Fulton Forge Student Research Expo are encouraged to download this personal QR code and include it within your poster. This allows expo attendees to explore more about your project and about you in the future.
Right click the image to save it to your computer.
Featured project | Spring 2025
After learning about FURI in his FSE 100 Introduction to Engineering class, computer systems engineering undergraduate student Reeyan Choudhury decided to submit a proposal to explore his fascination with artificial intelligence, or AI. Under the guidance of his FSE 100 instructor Adwith Malpe, a Fulton Schools assistant teaching professor of computer science and engineering, and Ryan Meuth, a Fulton Schools associate teaching professor of computer science and engineering, Choudhury aims to reduce the power consumption of large language model AI tools.
What made you want to get involved in this program? Why did you choose the project you’re working on?
I got involved with the program because my Professor Malpe introduced me to the program and helped me craft my proposal. It’s all thanks to him, along with my mentor Dr. Meuth, that I got involved with and am so successful in this program. I chose my project because I’ve always had an interest in AI since GPT-3’s inception. Though AI is amazing technology, as its abilities have advanced rapidly with the advent of new algorithms and tools, its electrical power requirements have increased exponentially in tandem. I find this very concerning.
How will your engineering research project impact the world?
While I don’t think my research project will change the world in a large way, I do hope it could spark conversations on the massive power usage of these large language models, or LLMs, like ChatGPT. Particularly, one task that wastes a lot of power is producing text that is largely never read and skimmed at best. Most people ask these LLMs a question and get a multi-paragraph answer, with the only useful information being at the bottom. As a result, users just ignore the big body of text and look at the last few sentences. All the ignored text costs power to create — lots of power. I hope that my research’s impact, if anything, will be to prompt more extensive research on ways to reduce and optimize the energy cost of these LLMs.
How do you see this experience helping with your career and advanced degree goals?
This is my first foray into research, which will help me get into research labs next semester. It also gives me valuable real-world experience, which is very different from academic assignments. This gives me more experience for my computer science classes and for a potential doctoral degree. It also benefits my career goals through real work experience.
What is the best advice you’ve gotten from your faculty mentor?
The best advice I’ve gotten was to join FURI. If I hadn’t gotten the encouragement, I know for a fact I wouldn’t have even attempted to submit a proposal because I would have believed that I wasn’t qualified enough, didn’t know enough, didn’t have enough experience, wasn’t good enough or the like. But I was told to just go for it, and this advice paid dividends. I’m now the workshop facilitator for a robotics club and undergraduate teaching assistant for a class on top of FURI research.
Why should other students get involved in this program?
On top of the obvious resume and recognition benefits, it’s an amazing experience that teaches you responsibility, hard work and how to conduct real-world research. It’s an experience no class can replace.
