Harshita Narnoli
Biography
I'm a Ph.D. Candidate in Computer Science. I am researching large language models, in-context learning, and developing resource-efficient strategies for models. My research investigates the identification and characterization of model strengths and their effects on downstream tasks. I have experience in model evaluation, machine learning experimentation, and AI safety.
I earned my Master's degree in May 2024 from the University of Arizona. Before this, I earned a Bachelor's degree in Computer Science and Engineering through MAKAUT in 2017. I began my career as a web developer, focusing on Java and the Spring MVC framework. During this time, I led a technology team at Nomura Research Institute on a project targeting the Shanghai and Shenzhen stock exchanges. Afterward, I moved to a Senior Software Developer role at Alien Brains, where I worked with Ruby on Rails, managed frontend and backend teams, and served as a Scrum Master.
Research Interests
Natural language processing, Machine learning, Artificial Intelligence
What long-term project do you want to work on?
In the long term, I want to work on building strategies to have safer and robust language models that better understand human intent and handle diverse inputs responsibly. My focus is on studying how model behavior varies across different contexts and finding ways to connect the dots across contexts to generate better results.
What do you enjoy most about your work?
I enjoy the process of figuring out how and why models behave the way they do, especially when the behavior is unexpected or inconsistent. There’s something very satisfying about digging into data, testing how models behave in different scenarios, and gradually uncovering patterns that aren’t obvious at first.
Working on language models in particular feels impactful because even small improvements in understanding or robustness can meaningfully change how these systems behave in real-world settings.
What are your career goals
I want to develop reliable, safe, and interpretable AI systems, particularly large language models that can be trusted in real-world applications. I want to contribute to research that improves model robustness, reduces harmful behavior, and better aligns model outputs with human intent. In the long term, I want a Researcher role in a company where I can better understand how models behave and turn that into practical, responsible systems used in real-world applications.
Tell us something interesting about yourself!
I enjoy putting my best effort into everything I do, failing to give up without trying. Outside of academics, I have a creative side. I love dancing and painting, which allows me to relax and better express myself.