Hayden Housen

San Francisco, CA · hayde-remove-n@haydenhousen.com
PDF Resume

Co-founder at Sonauto (YC W24), building an AI music editor that turns prompts, lyrics, and melodies into full songs in any style. Studied computer science at Cornell University. Previously, a software engineering intern at Vocode (YC W23) and an intern on the Machine Learning Team at Ada.

Researched unsupervised object discovery with Dr. Ellis as a sophomore and paraphrase identification (published in NeurIPS 2022) with Dr. Sernam Lim as a freshman. Researched automatic classroom lecture summarization using AI and deep learning in high school. Understands machine learning in production and full-stack web development. Developed a state-of-the-art neural text summarization system with 400+ stars on GitHub. Publishes guides for cybersecurity challenges. Enjoys running year round and skiing in the winter.

This site was generated using HUGO from an open source theme via Netlify.

Netlify Status

Experience

Co-founder and CTO @ Sonauto (YC W24)

AI Music Generator/Editor

Sonauto is an AI music editor that turns prompts, lyrics, or melodies into full songs in any style. For example, in a few minutes with Sonauto you can make an original birthday song for your friend, sung by Frank Sinatra.

Jan 2023 – Present

Software Engineering Intern @ Vocode (YC W23)

Open-source tool to build voice-based LLM applications

  • Collaborated directly with founders as a pivotal engineer to shape Vocode’s pioneering AI-driven call automation solutions.
  • Demonstrated versatility as a fullstack developer by building the FastAPI backend, open-source self-hosted service (Python and asyncio), and frontend dashboard (Next.js), while also resolving issues and reviewing pull requests from the community.
  • Evaluated the latencies of multiple LLMs, speech-to-text APIs, and synthesis services to enhance Vocode’s performance.

May 2023 – Aug 2023

Undergraduate Researcher @ Cornell

Machine Learning and Artificial Intelligence Research

Sep 2021 – May 2023

Machine Learning Intern @ Ada Support

Improved Ada’s intent classification pipeline

  • Improved Ada’s production accuracy by 8% using only 3% of production data by developing a novel intent classification pipeline.
  • Conducted >60 experiments and trained >110 models to determine the most accurate methodology.
  • Experimented with knowledge transfer, unsupervised learning of sentence embeddings, multi-task learning, and contrastive losses in the context of transformers and support vector machines.

May 2022 – Aug 2022

Machine Learning Intern @ Ada Support

Improved multilingual understanding for Ada’s AI chatbots

  • Led the discovery and experimentation phases of a project to enable Ada chatbots to better understand non-English languages.
  • Wrote a data processing pipeline to efficiently clean and analyze 9 billion chat messages for machine learning models.
  • Researched novel techniques in multilingual intent prediction and cultivated skills in PyTorch, transformers, and pandas.

May 2021 – Aug 2021

lecture2notes

Summarizing Lecture Videos by Classifying Slides and Analyzing Text

  • Created a state-of-the-art system to summarize classroom lectures using PyTorch, transformers (BERT), optical character recognition, speech to text, and convolutional neural networks. Source on GitHub. Learn more in the research paper.
  • Named a top 300 scholar in the 2021 Regeneron Science Talent Search, the nation’s oldest and most prestigious science and math competition for high school seniors.
  • Deployed ML pipeline in production via a full-stack website powered by Docker, Flask, Celery, Bootstrap, and Stripe.
  • More info on the project page.

Sep 2019 – Jan 2022

TransformerSum

Open-Source Neural Summarization Library

  • Furthered research in neural-network text summarization with a focus on long document summarization. 310+ stars on GitHub.
  • 4.45x smaller than the state-of-the-art model but 94% as accurate at release. 10+ pre-trained models available.
  • Rewrote researchers' code with enhanced performance and a focus on code readability and thorough documentation.
  • More info on the project page.

Mar 2020 – Oct 2020

Cybersecurity Challenges

Ethical Hacking Skills

  • Placed 23rd (top 0.7%) in 2021 National Cyber Scholarship Competition.
  • Placed in top 3% on average in PicoCTF 2019/2021/2022 competitions. Wrote technical guides with over 94,000 views to document my learning and help others.
  • Continuously practicing cybersecurity principles by solving HackTheBox.com machines and publishing writeups.
  • Learned ethical hacking skills including web exploitation, cryptography, reverse engineering, and binary exploitation. Worked with popular tools included in Kali Linux.

Sep 2019 – Present

Projects

Collection of Projects Created by Hayden

lecture2notes

For this project, I was named a top 300 Regeneron STS scholar. Lecture2notes is a state-of-the-art system to summarize classroom lectures using machine learning.

Learn More

TransformerSum

Models to perform neural summarization (extractive and abstractive) using machine learning transformers. 400+ stars on GitHub.

Learn More

Will I Have a Snow Day

130,000+ users in winter 2024. Simply enter your zip code and an advanced AI will calculate your chance of having a snow day for the next few days.

Learn More

Unsupervised Object Discovery

An implementation of several state-of-the-art machine learning models that discover objects in images without being told what an object is.

Learn More

PicoCTF 2019 Writeup

My solutions to the PicoCTF 2019 computer security competition. I scored 13,900 points (top 3.8%) during the competition but have since completed all the problems to reach 34,201 points.

Learn More

National Cyber Scholarship Competition 2021 Writeup

I was named a National Cyber Scholar with Honors for placing 23rd out of 3,277 (top 0.7%) in this cybersecurity competition.

Learn More

HH Personal Website

This website is hosted by Netlify and is generated using my own custom open source theme using Hugo.

Learn More

GPT Impostor for Discord

Impersonate your friends on Discord using the latest research in AI and machine learning. Originally developed during BigRed//Hacks @ Cornell.

Learn More

Advent of Code

My Python solutions to 4+ years of Advent of Code puzzles.

Learn More

Speaker Change Detection

An implementation of a machine learning architecture that detects when the current speaker changes in an audio file.

Learn More

PicoCTF 2021 Writeup

My solutions to the PicoCTF 2021 computer security competition. I scored 5,440 points (top 1.1%) during the competition as a solo player and placed 25th among US Middle/High School students.

Learn More

PicoCTF 2022 Writeup

My solutions to the PicoCTF 2022 computer security competition. I scored 12,000 points (top 3.2%) during the competition as a solo player and placed 248th.

Learn More

HackTheBox CyberSanta 2021 CTF Writeup

Write-ups for various challenges from the 2021 HackTheBox 2021 Christmas CTF. Solved all web, crypto, and forensics puzzles.

Learn More

HackTheBox Machine Writeups

Write-ups and tutorials for various cybersecurity challenges from HackTheBox.

Learn More

DocSum

A tool to automatically summarize documents using the BART Machine Learning Model.

Learn More

AI Respiratory Doctor

A flask web app template for use with machine learning projects. Currently contains complete example code to run a fully functional X-Ray diagnosis AI.

Learn More

Personal Server

I maintain a personal server where I self-host applications such as Nextcloud, Guacamole, and more.

Learn More

FreeCodeCamp Collection

Completed about 400 hours of coursework. Built 10 front-end projects. Completed 347 coding challenges.

Learn More

Education

Cornell University

Bachelor of Science
Computer Science

Info: College of Engineering. Dean’s Honor List. Previous president of the Cornell Cybersecurity Club.

2021-2025 (Expected Graduation)

Pawling Central High School

Advanced Regents Diploma with Honors
GPA: 4.0

Info: Always enrolled in highest level courses. Conducted research into machine learning & computer vision through Science Research program. Took every available computer science course.

2017-2021

Skills

Languages
  • Python
  • JavaScript/TypeScript
  • Java
  • HTML
  • CSS
  • SQL
  • OCaml
  • C
  • Bash
Machine Learning
  • PyTorch
  • transformers (GPT)
  • scikit-learn
  • NumPy
  • Lightning
  • pandas
  • OpenCV
  • Spacy
Web
  • React
  • Next.js
  • Tailwind CSS
  • FastAPI
  • Flask
  • React Native (Expo)
  • Bootstrap
  • web scraping
DB and DevOps
  • PostgreSQL
  • Docker
  • Supabase
  • Azure
  • AWS
  • MongoDB
  • MySQL
  • Firebase
  • CI/CD
  • Git