Harsh Maheshwari
Computer Science & Mathematics Student
Software Engineer • Machine Learning Enthusiast • Researcher
About Me
I'm a Computer Science and Mathematics student at Pennsylvania State University with a passion for software engineering, machine learning, and research. Currently maintaining a 3.8/4.0 GPA, I'm dedicated to applying my technical skills to solve real-world problems.
My experience spans from developing AI-driven mental health platforms to conducting research on bias in large language models. I've worked with diverse technologies including React Native, Firebase, Flask, and various machine learning frameworks.
As a Chief Technical Officer at Marble, I've led development teams using Agile methodologies and delivered successful products that make a positive impact. I'm particularly interested in the intersection of technology and healthcare, where I've contributed to applications that support medical professionals and patients.
Experience
- Directed the development of a cross-platform mobile application for managing pediatric and adult heart disease, built with React Native and JavaScript, leveraging Firebase for real-time data synchronization and streamlining patient record access for 500+ users.",art disease, built with React Native and JavaScript, leveraging Firebase for real-time data synchronization and streamlining patient record access for 500+ users.
- Collaborated in an agile team of 5, successfully delivering the app to the university by the deadline.
- Conducted extensive beta testing with 20+ users to ensure the app's functionality and user experience.
- Publishing a research paper as the lead author on the bias by LLM's on 20+ stereotypical subjects by Llama 2 7B using graphs.
- Developed Python scripts and Jupyter notebooks to automate data collection, leveraging Flask API to retrieve model responses from various LLM models on Hugging face
- Led the development and launch of an AI-driven mental health platform, managing technical teams with Agile and Scrum methodologies, and achieved 50+ downloads in the first week on the App Store.
- Secured $7,500 in awards and engaged with over 300 potential users to tailor product features.
- Spearheaded a website using Node.js, Next.js, React, and TypeScript, leading a team of 4 members, delivering the MVP in under one month
- Built REST API endpoints using Flask to connect with AWS, Firebase, OpenAI and Eleven Labs calls for data retrieval, enabling generative AI–powered insights and AI-powered voice calling in real time.
- Delivered the application to be launched to over 1,000 social workers in supporting 100,000+ child abuse victims.
- Architected and deployed a Python-based RAG (Retrieval-Augmented Generation) backend, leveraging MongoDB for rapid data retrieval and seamless AI query execution—scaling to support 1,000+ social workers.
Education
BS in Computer Science and BS in Mathematics
GPA: 3.8/4.0
Awards
- President Walker Award
- President Sparks Award
Relevant Coursework
- Data Structures & Algorithms
- Machine Learning
- Artificial Intelligence
- Database Systems
- Linear Algebra
- Discrete Mathematics
- Calculus & Analysis
- Probability & Statistics
Projects
Achieved an accuracy of 94% and 80% for CNN models detecting brain tumors and Alzheimer's. Utilized 300+ DICOM files(CT Scans) to develop an algorithm for a 3D model of the brain. Rewarded with 1st place amongst 300 people in the category for usage of Generative AI.
Developed 4 image classification CNN models to identify and differentiate between vehicles, animals, flowers, fruits and vegetables with accuracy ranging from 85% to 95%
Collaborated with a team of five to design and create a real-time ASL Translator app with an accuracy of 87%, delivering third-place success in a competitive Hack PSU event.