Hi, I'm Koral

Software Engineer specializing in AI

Resume

About Me

I'm a Software Engineering student at the University of Waterloo with a passion for building innovative solutions that make a real impact. With experience at companies like BitGo, AtoB, and D2L, I've worked on everything from AI-powered GTM systems to multi-agent frameworks.

My projects have generated significant value – from winning the Canada-Wide Science Fair to working on systems that projected $8M+ ARR. I love tackling complex problems at the intersection of software engineering and AI.

University of Waterloo

Education

University of Waterloo

Bachelor of Software Engineering

3.9/4.0 GPA • Sep 2023 – Apr 2028

AI Specialization

Languages

Python
C/C++
Ruby
JavaScript
TypeScript
SQL
Java
Assembly

Tools & Frameworks

Docker
AWS
React
Node.js
Django
Rails
TensorFlow
PyTorch

Interests

Chess
Poker
Table Tennis
Competitive Programming
CTFs

Work Experience

BitGo logo

BitGo

Software Engineering Intern

Palo Alto
Sep 2025 – Dec 2025

Enhanced security infrastructure and hardened SDK for cryptocurrency custody platform.

  • Built Rust-based linter using Trustfall and GraphQL to enforce SHA pinning, protecting 320+ repositories

  • Improved BitGo SDK OpenSSF Scorecard from 5.4 to 7.5 by remediating npm vulnerabilities (XSS, DoS, credential leakage)

AtoB logo

AtoB

Software Development Intern

San Francisco
Jan 2025 – May 2025

Built AI-powered systems for lead scoring and customer matching, creating significant business value.

  • Built ML lead scorer and autoencoder for customer matching, boosting sales ROI ($8M+ ARR projected)

  • Created data pipelines: UTM tracking (500K+ events/month) and UCC-1 web scraper ($150K+ data)

  • Developed semantic matching for user-uploaded fuel statements to SQL relations

D2L logo

D2L

Software Development Intern

Toronto
May 2024 – Sep 2024

Developed AI-powered educational tools and multi-agent systems for automated course QA.

  • Built multi-agent framework for automated course QA using AWS Step Functions and Lambda

  • Created Brightspace tool for FAISS knowledge graphs and semantic course search

  • Designed custom RAG models for AI tutoring, integrated with React UI

My Projects

A few of my projects — all on GitHub

Sematic

Sematic

Collaborative whiteboard that turns voice and video into structured diagrams in real-time. Powered by Gemini 2.0 Flash and AWS Amplify Gen 2 for spatially-aware, multimodal collaboration.

HighlightsAWS Campus Champions: Best Use of DynamoDB Streams @ Hack the North

Gemini 2.0 FlashAWS Amplify Gen 2DynamoDBCognitoLambdaReact Flow
Admini

Admini

Led a 5-person software team to develop a centralized government contracting platform. Built a fully responsive landing page and 10+ application pages using React with MUI and Tailwind CSS.

Highlights5-person team leadCentralized platformAWS infrastructure

AWSEC2DynamoDBS3ReactPythonJavaScriptTypeScript
3D Octree Compression

3D Octree Compression

Developed a 3D object compression algorithm using octrees, achieving up to 99% memory reduction. Built a real-time OpenGL visualizer using MVC design pattern.

Highlights99% memory reductionReal-time visualizationMVC design pattern

C++OpenGLComputer Graphics
FourSight

FourSight

Built a 95% accurate neural network to classify 12 types of cancer from microarray samples. Won the Canada-Wide Science Fair and represented Canada at the EU Contest for Young Scientists (2nd place).

Highlights95% accuracyCanada-Wide Science Fair Winner$20K fundingPublished to CSF Journal

PythonJavaScriptTensorFlowMatPlotLibDjangoDockerHerokuPandas
Autonomous Car

Autonomous Car

Built a real-time lane detection system with OpenCV canny edge detection and hough transforms. Overlayed vehicle and traffic sign tracking using YOLOv4-tiny.

HighlightsReal-time detectionLane detectionObject tracking

PythonOpenCVNumPyYOLOv4-tiny
SentiTrader

SentiTrader

Developed a medium-frequency sentiment analysis trading bot that scrapes r/worldnews. Live-tested Keras and Sklearn models reaching 12% annualized returns.

Highlights12% annualized returnsLive tradingSentiment analysis

PythonKerasSklearnSentiment Analysis
AirBoard

AirBoard

Built a hands-free typing system using MediaPipe hand tracking to control the mouse and keyboard.

Highlights24-hour buildHands-free typingHand landmarks

PythonOpenCVMediaPipe
PrsntAI

PrsntAI

A startup that transforms speech into presentation slides live using AI. Fine-tuned GPT-3.5 and used DALL-E for image generation. Deployed to prsntai.com using Vercel.

HighlightsLive speech-to-slidesFine-tuned GPT-3.5Multi-framework implementation

PythonJavaScriptGPT-3.5DALL-EReactDjangoFlaskVercel
Songsnap

Songsnap

2024 UofTHacks project. Website that inputs photos and generates Spotify playlists that encapsulate the moment using GPT-4 Vision and fine-tuned GPT-3.5.

HighlightsUofTHacks 2024Photo-to-playlistGPT-4 Vision integration

PythonGPT-4 VisionGPT-3.5CoherePostgreSQLSpotify APIAuth0Flask
NoteBot Bryan

NoteBot Bryan

Built at DeltaHacks 2024, Bryan is an AI assistant that listens to lectures and generates real-time notes using Whisper and GPT-3.5.

HighlightsDeltaHacks 2024Real-time transcriptionMarkdown note generationMultithreaded PyGame UI

PythonGPT-3.5WhisperPyGamePyAudioThreading
ML Experiments

ML Experiments

Personal repo for ML/DL experiments: CPH survival models, decision trees, ResNet-50 saliency maps, and Kaggle code. Inspired by Hands-On Machine Learning.

HighlightsCPH survival modelsDecision tree classifiersResNet-50 saliency mapsKaggle competition code

PythonScikit-LearnKerasTensorFlowResNet-50
Histopathology AI

Histopathology AI

Built an artificial neural network from scratch to classify cancer in histopathological and blood images, with a Flask web app for image-based diagnosis.

HighlightsCustom neural networkMedical image classificationFlask web interface

PythonJavaScriptTensorFlowMatPlotLibFlaskNumPy
COVIDTracker

COVIDTracker

COVID-19 spread simulation using 2008 Beijing taxi data and PyGame. Users can control infection parameters and observe how the virus spreads over time.

HighlightsGraph-based simulation2008 Beijing taxi dataInteractive infection modeling

PythonPyGameNumPy
Competitive Programming

Competitive Programming

Journey from Python to C++. Solutions and notes for major contests (AOC, CCC, USACO, CodeForces, etc.), plus scripts for stress-testing and code templates.

HighlightsAdvent of Code, CCC, USACO, CodeForces, and moreStress-testing scriptsCode templates (e.g., trie)17th place in Canada (picoCTF 2022)

PythonC++AlgorithmsData StructuresCompetitive Programming
Planets

Planets

A partial 3D solar system simulation built in 1 day. Uses ForceGraph3D for orbital mechanics and Three.js for realistic texture maps. Fully interactive 3D environment.

HighlightsBuilt in 1 day3D orbital mechanicsInteractive exploration

ReactThree.jsWebGLJavaScript

Get In Touch

I'm always interested in new opportunities. Whether you want to discuss a project, internship, or just say hello, feel free to reach out!

Email

kulacoglukoral@gmail.com

Send Email

Location

Toronto, Canada

Canadian & Turkish Citizen