$(whoami)
hi, i'm tiffany! currently studying cs & math @ purdue, and spent the last two summers interning at AWS. i'm drawn to problems involving systems, data, and building reliable software at scale, including backend infra, ml & agents, robotics, and fintech.
as an engineer, what drives me is building things that create real value and impact for users — ideally while working on problems i personally find exciting.
outside of coding, you can usually find me climbing/hiking, taking photos on my Sony a6700, or drinking way too much coffee and boba.
Joining Stripe's San Francisco office.
Designed and built rules-based search indexing for a distributed document store on DynamoDB and OpenSearch, routing documents across dedicated indices to bound index sizes and improve query performance.
AWS · Java · DynamoDB · OpenSearch
Expanded an AWS-native ticket and issue management API serving 130M+ daily requests, adding priority and label-based filtering across 7 operations.
AWS · Java · API Design · Testing
Contributed to NLP and data-pipeline work during KeywordsAI's early stages.
Python · NLP
🏆 Berkeley AI Hackathon — Top 10 Finalist out of 400 teams · Hackers' Choice Winner
A multi-agent computer-use harness (MCP server) that lets coding agents QA their own work. It launches your app in a sandbox, splits the UI into regions, and runs one agent per region to screenshot, click, and verify by pixel across web, Electron, and mobile.
Python · MCP · Claude · Computer Use
A RAG pipeline for source-backed Q&A across 450+ pages of Purdue policy docs, using LangChain, Pinecone, and Gemini.
Python · LangChain · Pinecone · Firebase · Gemini
A financial news sentiment pipeline using FinBERT to score articles across 13 assets and generate hourly buy/sell/hold signals from short-term sentiment shifts, visualized in a Streamlit dashboard.
Python · Pandas · PyTorch · Hugging Face · Streamlit
A full-stack flight tracker with an interactive 3D globe of past flights and reports that aggregate by airline, route, and date to surface stats like total flight time, miles, and on-time rate.
Python · Flask · PostgreSQL · React · Pandas
An interactive codebase visualizer for developer onboarding that uses AST parsing to map function calls and dependencies, with a Pinecone-powered RAG chatbot for context-aware queries.
React · Express/Node.js · MongoDB · Pinecone · OpenAI
Building an agent that can autonomously reproduce machine learning security research papers.
Python · PyTorch · LLM Agents
Worked on the RAG pipeline for BoilerCheck, an AI assistant that answers questions over Purdue policy docs, benchmarking different embedder and reranker combinations to improve retrieval quality.
Python · LangChain · Pinecone · Firebase · Gemini
Led a 6-person team building a real-time celebrity news feed for a Social Stock Exchange, with an LLM + web-scraping pipeline and a trend-ranking algorithm based on velocity, mention frequency, and recency.
Node.js · Axios · Cheerio · Gemini · NewsAPI · Supabase
Built a vision-guided robotics system for autonomous drumming on a Baxter robot, using OpenCV AprilTag localization and inverse kinematics for precise, dynamically recalibrated strikes.
Python · OpenCV · ROS
Engineered robot localization, path-planning, and auto-aiming with AprilTags, odometry, and PID/state-space control across the drivetrain, vision, and game-piece subsystems.
Java · Computer Vision · PID Control · AprilTags
1 of 75 students selected for a rigorous for-credit summer program at Penn's Jerome Fisher M&T program, exploring the intersection of technology and business. Built a team engineering project and got hands-on exposure to startups, product management, and tech entrepreneurship.
Python · CNN · Raspberry Pi · React Native · Firebase · Twilio
Selected for the computer science track at Penn Engineering's summer program, focused on data analysis and visualization with Pandas, NumPy, and Matplotlib to explore and draw insights from datasets.
Python · NumPy · Pandas · Matplotlib
i tend to gravitate toward videos on system design, recent tech/ai news, and game theory or riddle-style problems.
i'm currently open to new opportunities in SWE, ML, quant trading, or any role where i get to work on cool, challenging, and impactful problems! whether you have a question, want to collaborate, or just want to say hi — feel free to reach out.
