Present: I am a software developer and incoming freshman studying Informatics at the University of Washington. My main interest is building software that turns messy business, education, and institutional workflows into clear products people can actually use. I am especially interested in AI/ML applications where models are not just demos, but part of a useful workflow: admissions tools, financial systems, student platforms, image models, automation dashboards, and decision-support products.
My work has focused on practical software projects with business value: a College Essay Prompts API with 1,700-2,000+ prompts, an OpenPath education platform for nonprofits, web applications for college admissions and financial aid at Cledge and Kollegio AI, and a UW SEAL software proposal aimed at simplifying student reimbursement workflows. I like the middle ground between engineering and strategy: deciding what should be built, building it, and then making it usable enough that it can survive outside a portfolio.
AI/ML: I have built applied machine learning projects including an Alzheimer's detection model from brain imagery and a street segmentation model for identifying obstacles in urban scenes. I am interested in how AI systems can support real users in education, business operations, risk modeling, and productivity, while still being evaluated carefully enough to avoid turning guesswork into product features.
Leadership: As a secondary part of my work, I founded and lead StuImpact, where our team connects students with opportunities, events, mentorships, and volunteer programs. StuImpact reflects the same product instinct I bring to software: find an inefficient system, understand the people inside it, and build something that helps them move.
At UW, I hope to keep developing as a software developer with a strong business lens, especially in AI/ML applications, education technology, automation, product engineering, and tools for student opportunity.
I built a prototype API for accessing college essay prompts through a simple request flow. The project includes roughly 1,700-2,000+ prompts, with request turnaround times around 269-1006 ms depending on request size. I designed it for students, counselors, educators, college-advising firms, and startups that need structured admissions data inside their own products. The project did reach 500 user accounts (using the api) before I had to sunset due to api costs.
Alzheimer's Detection Model and Model Street Segmentation
I built applied AI/ML projects around image understanding: a JavaScript model for Alzheimer's detection from brain imagery and a street segmentation model for identifying obstacles in city environments. These projects are early examples of the AI work I want to keep developing: useful models wrapped in real interfaces, not just notebooks.
At the UW Sensors, Energy, and Automation Laboratory, I worked hard on the Blueberries software proposal effort for a $62K Student Technology Fee project. The goal was to simplify UW's reimbursement workflow for students, a business-process problem inside a large institution with real cost, usability, and trust constraints.
OpenPath is a free educational platform built to help grassroots nonprofits access teaching resources and practical knowledge. The site supports 20+ nonprofits and gave me experience turning an idea into a usable product for organizations with limited time and technical capacity.
I have been building games since 2019, primarily with Unity and C#. Across personal projects and game jams, I have published 7 games and explored 3D mechanics, interactive systems, and larger AAA-inspired design goals. This work shaped how I think about user experience, feedback loops, and the craft of building things people actually want to use.
May 2024 - Aug 2024 | Remote
Selected from 5,300 applicants into a 20-person intern cohort. Worked in cross-functional teams on improving Kollegio AI's software systems, efficiency, and education technology products for tools serving 100,000+ student users.
Jun 2023 - Jan 2024 | Seattle, Washington
Built Flask, Next.js, React, MongoDB, and Azure-backed applications for college admissions and financial aid workflows. Worked on authentication, AI training interfaces, Chrome extensions, Google add-ons, and user-facing product improvements.
Sep 2023 - May 2024 | Remote
Led the technical direction for a digital marketing organization, managing interns and building web tools with Python, Flask, JavaScript, HTML, and Bootstrap. Developed automation systems for email campaigns, social media scheduling, and AI-supported content generation.
JavaScript, machine learning, image labeling | Oct 2023 - Dec 2023
Built a JavaScript-based model for detecting Alzheimer's indicators from top-down brain imagery, reaching approximately 90% detection precision in project testing.
JavaScript, image sensing, machine learning | Oct 2023 - Dec 2023
Developed a street environment segmentation model for identifying different obstacles and objects in city scenes.
Risk math, portfolio strategy, modeling | 2022 - Present
Created an algorithmic trading model over four years of experimentation, using risk math and portfolio strategies. In one three-month period, the model returned 40% under my testing and management.
Software: Python, JavaScript, React, Next.js, Flask, MongoDB, Azure, HTML, CSS, Bootstrap
AI and Data: Machine learning, TensorFlow, image labeling, segmentation, AI training interfaces
Product: Web engineering, full-stack development, software design, information security
Leadership: Team leadership, project management, nonprofit operations, student mentorship
Languages: English, Tamil