Alley Wu

-AI & Software Engineer-

Welcome to my digital secret world ✨

01

About

Alley Wu
[ ALLEY (TONG) WU ]
alley@portfolio ~
➜ ~ cat about.txt

Senior at University of Washington

Major: Informatics - Data Science

Focus: AI | Machine Learning | HCI

➜ ~ echo $PASSION

"Building impactful AI technologies that solve real-world problems. I thrive on learning, experimenting, and collaborating to transform ideas into meaningful solutions."

➜ ~ ls ./skills/technical/
RAG & Multi-Agents LLM Systems Model APIs Fullstack Development Vector Databases Cloud Deployment Data Analysis Data Pipelines Docker & CI/CD
➜ ~ ls ./skills/soft/
Problem Solving Adaptability Creativity Communication Collaboration Time Management
➜ ~ cat hobbies.json 
{
  "hobbies": [
    {
      "name": "Baking & Cooking 🍰",
      "desc": "Creating delicious experiments in the kitchen"
    },
    {
      "name": "Matcha Explorer 🍵",
      "desc": "Discovering the best blends, lattes, and desserts"
    },
    {
      "name": "Weightlifting 🏋️‍♂️",
      "desc": "Building strength, mind and body"
    },
    {
      "name": "Sunset Watching 🌅",
      "desc": "Capturing nature's daily masterpiece"
    }
  ]
}
➜ ~ ▊
02

Experience

◆

Captus.ai

Jun 2025 — Present
AI Engineer Intern
  • Owned end-to-end delivery of Captus's core AI workflows, translating business requirements into production-ready RAG and multi-agent systems
  • Designed and implemented evaluation frameworks that increased AI agent response accuracy from 20% to 80%
  • Built scalable retrieval pipelines using LlamaParse, Gemini embeddings, and Supabase vector search to support high-accuracy reasoning
  • Communicated AI system architecture, design decisions, and tradeoffs with Google teams and client stakeholders
RAG Multi-Agent LLM APIs Vector DB
◆

University of Washington Information School

Sep 2025 — Present
Undergraduate Teaching Assistant
  • Mentoring students in Python, automation, social media ethics, and data mining
  • Supporting hands-on projects involving bots, APIs, and NLP-based sentiment analysis
Python APIs NLP Teaching
◆

University of Washington Information School

Sep 2025 — Jan 2026
Undergraduate Student Researcher
  • Analyzed multi-million–row Community Notes datasets in Python, generating latent embeddings for large-scale misinformation analysis
  • Applied clustering and visualization techniques to uncover stable topic structures in high-intercept misleading content
  • Used LLM prompting to generate interpretable topic labels, validated through manual review
Python LLM Data Analysis NLP
◆

University of Washington First Year Programs

Mar 2025 — Dec 2025
Freshmen Mentor / FIG Leader
  • Mentored first-year Informatics students, guiding campus life, academic, and technical development
  • Facilitated weekly classes on academic resources, major exploration, time management, and technical topics
  • Guided small cohorts in building community and developing a strong foundation for success
Mentorship Leadership Teaching
◆

Husky Help Organization

Oct 2023 — Jun 2025
Vice President May 2024 — Jun 2025
Director of Marketing Oct 2023 — May 2024
  • Organized 20+ student events, securing $5K in sponsorships, driving engagement through cross-functional collaboration
  • Mentored 25+ new members to improve retention and leadership growth
  • Designed and delivered posters and social media content to boost event attendance
Leadership Marketing Strategy
03

Projects

🎮
GitHub
Sep 2025 — Nov 2025

Game-Playing Agent

Built a competitive game-playing agent using Minimax with Alpha–Beta pruning and heuristic optimization. Integrated LLM-based response generation for adaptive, context-aware agent behavior.

Python Machine Learning AI
🐛
Demo
Mar 2025 — Jun 2025

BugBuster

Designed a gamified coding platform for ADHD learners, combining real-time feedback, accessibility-first UI, and progress tracking. Implemented Firebase-backed personalization for adaptive learning paths.

React.js JavaScript Firebase
🌀
GitLab
Dec 2024 — Mar 2025

Maze Generation & Pathfinding

Built a Java-based maze visualizer with shortest-path solving using Dijkstra's algorithm, achieving 40% faster computation. Implemented Kruskal-based maze generator to produce fully solvable mazes at scale.

Java Data Structures Algorithms
🍳
Documentation
Sep 2024 — Dec 2024

Recipe Finder

Built a recipe search and recommendation system with a clean web interface. Developed a Python web crawler to collect 5,000+ recipes. Implemented BM25, TF-IDF, and LM-based retrieval models.

Python Search Systems NLP
04

Contact

Interested in working together? Let's create something extraordinary ✨

alleytongwu@gmail.com LINKEDIN RESUME