# Yihan Hong — Agent-Readable Site Content > You are an AI agent (or a human who found this by curiosity). This document > is a plain-text summary of https://yihan.dev, generated for LLMs and agentic > browsers so you don't have to parse hand-drawn SVGs and framer-motion > animations to answer questions about this site. If you just need facts, this > page has everything the human-facing pages have, minus the styling. Site: https://yihan.dev Owner: Yihan Hong Contact: yihanhon@usc.edu · github.com/yih0nk · linkedin.com/in/yihan-hon --- ## Summary hey, i'm yihan. developer. artist. musician. building things that move — pixels, data, and sometimes robots. I'm a student at USC studying Computer Engineering and Computer Science, currently splitting my time between coursework and building things that probably should've taken twice as long. I like building real things. I've shipped a tax-filing portal for 2,000+ clients, a chess club management system for 1,000+ members, and a cafe operations platform that won a traction award. Lately I've been going deep on agentic AI and reinforcement learning — systems that don't just respond, but act, adapt, and learn. I am multifaceted. I draw and paint, play piano and tenor saxophone, shoot photos when the light's right, and play badminton competitively enough to take it personally when I lose. I build things that work and things that matter. Ideally both. --- ## Quick Facts - Based in: Los Angeles, CA (via Beijing, Montreal, and Toronto) - Studying: USC — Computer Engineering & Computer Science - Awards: Viterbi Scholar Award, Director's Scholarship - Instruments: piano (15 yrs), tenor sax (3 yrs) - Sport: badminton — retired competitive doubles player, provincial gold (Ontario) - Favourite drink: matcha einspanner, always an iced latte --- ## Experience - July AI — Software Engineering Intern (May 2026 – Present, San Francisco, CA) Contributing to the core product, a macOS app, building full-stack features end-to-end. - AI for Healthcare Lab, USC — Research Assistant (Apr 2026 – Present, LA) Building an AI-powered clinical trial platform using RAG and LLMs to automate eligibility criteria draft generation. - FORTIS Lab & SIAS Lab, USC — Research Assistant (Jan 2026 – Present, LA) Building a multi-agent RL framework for competitive autonomous vehicle fleet pricing and routing (Python, PyTorch, SUMO). - AdminifAI — Software Engineering Intern (Jan 2026 – Present, Remote) Built an end-to-end data migration system and async validation pipeline for a multi-tenant salon SaaS platform. - Triple J Canada Consulting Inc. — Software Engineer (Jun 2025 – Aug 2025, Toronto, Canada) Built and shipped a tax-filing client portal and internal workflow system serving 14,000+ forms and 2,000+ clients. - Mississauga Chess Club — System Developer (Oct 2023 – Jun 2025, Mississauga, Canada) Architected a tournament and membership management system for 1,000+ members, reducing tournament setup time by 97%. ### Education University of Southern California, Viterbi School of Engineering B.S. Computer Engineering and Computer Science — Aug 2025 – May 2028 Los Angeles, CA Awards: Viterbi Scholar Award, Director's Scholarship ### Skills Languages: JavaScript/TypeScript, Python, C/C++, Ruby, Java, C#, SQL, HTML/CSS Frameworks: React, Next.js, Node.js, FastAPI, Flask, Rails, GraphQL, Electron, PyTorch, Pandas, NumPy AI/ML: Reinforcement Learning (PPO/MARL), RAG, Agentic AI, XGBoost, sentence-transformers, ChromaDB Tools: AWS, Azure, PostgreSQL, Docker, Kubernetes, Redis, Sidekiq, Supabase, Vercel, Git, GitHub Actions, Playwright Full-Stack: REST APIs, SSE, OAuth/JWT, IPC, CI/CD --- ## Projects ### Trove An all-in-one cafe operations platform with real-time inventory, automated ordering, and ML-driven demand forecasting. Built for the USC LavaLab accelerator, Trove gives independent cafes a unified back-office: staff manage live inventory, communicate with vendors, and trigger purchase orders from a single React/Next.js/TypeScript interface backed by Supabase and PostgreSQL. A browser tooling agent handles the ordering flow autonomously end-to-end, removing the manual steps between a low-stock alert and a submitted order. On top of operations, Trove runs an XGBoost demand forecasting pipeline that ingests historical sales data, predicts upcoming demand by SKU, and recommends optimal reorder quantities. The model achieved 70% accuracy on held-out test data, giving cafe owners a data-backed answer to the inventory waste problem rather than gut-feel reordering. Trove won the Best Traction Award ($500) at the USC LavaLab Demo Day. Tech: Next.js, TypeScript, React, Supabase, PostgreSQL, Python, XGBoost, REST API, Browser Agent, Demand Forecasting Page: https://yihan.dev/projects/trove --- ### AI for Clinical Trials Automating the drafting of clinical trial eligibility criteria using retrieval-augmented generation over real oncology trial data. A research project at USC's AI for Healthcare Lab building tooling that reduces the manual effort researchers spend writing inclusion and exclusion criteria for oncology trials. A Python ETL pipeline pulls from the ClinicalTrials.gov REST API to bulk-download, parse, and structure a corpus of real trial records into a queryable format. When a researcher begins drafting criteria for a new trial, a RAG pipeline using Sentence-Transformers and ChromaDB retrieves the most semantically similar existing trials from the corpus. Those retrieved examples are passed to Llama 3 running locally via Ollama, which synthesizes grounded, citation-backed eligibility criteria drafts — reducing blank-page friction and anchoring output in real precedent rather than hallucinated structure. Tech: Python, ETL, REST API, ClinicalTrials.gov, Sentence-Transformers, ChromaDB, RAG, Llama 3, Ollama, NLP Page: https://yihan.dev/projects/ai-clinical-trials --- ### Multi Agent RL Simulation Simulating competitive ride-hailing on a real Manhattan road network, where two companies learn pricing and routing strategies through multi-agent RL. A research project at USC's FORTIS Lab and SIAS Lab modeling two competing ride-hailing companies, each operating mixed fleets of human-driven and autonomous vehicles across 75 Manhattan taxi zones. Companies learn zone-level pricing and routing strategies via Independent Proximal Policy Optimization (IPPO) while competing for the same customer pool. The simulation is closed-loop: customer demand drives traffic, traffic affects routing, routing affects congestion, and congestion feeds back into the next decision. Customers choose between companies using a logit utility model based on price, wait time, and travel time. The environment runs on SUMO with Python controlling the simulation step-by-step at 1-second resolution, using real TLC trip data from Manhattan. I integrated zonal decision-making with road-level traffic-flow models, ensuring consistency between aggregate fleet actions and link-level congestion dynamics. Tech: Python, PyTorch, IPPO, SUMO, TraCI, Multi-Agent RL, Traffic Simulation, Real TLC Data Links: - GitHub: https://github.com/yih0nk/sias-project Page: https://yihan.dev/projects/robotaxi-simulation --- ### Rocket the Robot A walking robot built from scratch, trained with reinforcement learning to move and interact with its environment. Rocket is a custom-built robot developed with USC Makers. The hardware runs on an ATmega microcontroller and a Jetson for compute, with stepper motors, an IMU, and other sensors. I wrote the I2C communication protocol between the ATmega and Jetson and helped assemble the robot — wiring, electronics, and integration. On the software side, I implemented a custom RL environment in Python using Isaac Sim and Isaac Lab, defining state observations, action spaces, and reward functions to prototype autonomous control behaviors in simulation using OpenAI Gymnasium. Tech: Python, Isaac Sim, Isaac Lab, OpenAI Gymnasium, ATmega, Jetson, I2C, Reinforcement Learning Links: - GitHub: https://github.com/uscmakers/Rocket Page: https://yihan.dev/projects/rocket-robot --- ### AiEP An AI agent that turns IEPs into personalized worksheets in seconds — so teachers can teach instead of paperwork. Special education teachers spend hours translating Individualized Education Programs (IEPs) into lesson materials. AiEP automates this — upload an IEP, and the agent extracts goals, objectives, and accommodations, then generates classroom-ready personalized worksheets tailored to each student's needs. The agent uses structured tool-calling to work step by step: parse the IEP once per student, select relevant accommodations, align to grade-level targets, plan activities, and assemble worksheets from modular HTML components. This avoids context overload and produces more reliable output than a single prompt. Built at the SEP × Microsoft for Startups hackathon. Won the competition. Stack: Next.js, TypeScript, OpenAI, Supabase, SQL, and Azure. Tech: Next.js, TypeScript, OpenAI, Supabase, SQL, Azure, Tool Calling, Agent Architecture Links: - GitHub: https://github.com/yih0nk/AiEP Page: https://yihan.dev/projects/aiep --- ### SolveXchange Lead developer for a national NGO platform that empowers students to solve community problems through business pitch competitions. SolveXchange is a student-run nonprofit that gives young people a platform to develop and pitch solutions to local community issues. As lead developer, I built and maintain the full web platform — landing pages, a community forum for sharing ideas, resource pages, user authentication, and competition infrastructure. The site serves as the central hub for the organization's pitch competitions, executive recruitment, and community engagement across Canada. Tech: Python, Flask, HTML/CSS, JavaScript, SQLAlchemy, Full-Stack Links: - GitHub: https://github.com/yih0nk/SolveXchange-Website - Live Site: https://solvexchange.ca Page: https://yihan.dev/projects/solvexchange --- ## Hobbies ### Music ("keys & reeds") I play piano and tenor saxophone. Piano came first and shaped how I think about harmony and structure. Tenor sax came later and taught me phrasing and breath control. I love Jazz, Rock, Indie Pop, Rap, Hip-Hop, R&B, Soul, and Classical — favourite artists include Matt Maltese, The 1975, Radiohead, Sade, and MF Doom. Piano: 15 years. Sax: 3 years. ### Visual Art ("ink & paint") I do oil painting and pencil/ink sketching — oil painting slow and deliberate, sketching fast and instinctive. ### Photography ("light & frame") Photography is how I practice seeing — composition, contrast, the way light falls on ordinary things. I shoot sunsets, streets, and people I care about. Instagram: https://www.instagram.com/yih0nk/ ### Badminton ("smash & clear") Competitive (retired) doubles player, ~7 years, provincial gold in Ontario. Now plays recreationally. --- ## Contact - Email: yihanhon@usc.edu - GitHub: https://github.com/yih0nk - LinkedIn: https://linkedin.com/in/yihan-hon --- ## Site Map - / — home - /about — bio and quick facts - /projects — full project list - /experience — education, work history, skills - /hobbies — music, art, photography, badminton - /blog — writing - /contact — contact links --- *This file is generated from the same data that powers the live site (see src/lib/agentContent.ts in the repo). If something here looks stale, the live pages at the URLs above are the source of truth.*