Dylan Dominguez Sulca

Contact Information:
NY ⋅ dylan.dosu@gmail.com ⋅ LinkedIn ⋅ GitHub

Education

CUNY, Hunter College
Masters of Arts, Computer Science
Expected Dec 2024
SUNY, Farmingdale State College
Bachelor of Science, Bioscience (Summa Cum Laude)
Sept 2017-May 2021

Skills

Languages: Python, Java, Bash, PowerShell, C++, HTML, CSS, JavaScript
Technologies: Azure, AWS, ServiceNow, MS 365, Power Platform, OpenCV, Pytorch, Scikit-learn, TensorFlow, Keras
Tools: Jupyter, Git, GitHub, Tableau, VS Code, 3D Slicer
Data Analytics: Data Analysis, Machine Learning, Model Production

Experience

New York City Office of Technology & Innovation
Cloud Engineer Internship
Jan 2024-Present
  • Developed and optimized cloud solutions using Azure to improve data analytics pipelines for NYC agencies.
  • Collaborated with engineers and stakeholders to manage SharePoint, OneDrive, and Power Platform, enhancing cross-agency collaboration and efficiency.
  • Led integration efforts for cloud infrastructure with backend services, focusing on security and scalability.
  • Architected and delivered cloud solutions for NYC agencies, boosting productivity and efficiency.
311 Internship
June 2023-Jan 2024
  • Collected and analyzed data to improve NYC services, working directly with customers.
Distributed Artificial Intelligence Research (DAIR) LabDAIR Lab
Master’s Research Thesis in Machine Learning
Jan 2024-Present
  • Researched and applied supervised ML models to enhance missing data imputation and model outcomes, improving algorithmic accuracy by 15%.
  • Explored automated algorithm selection based on metafeatures to reduce computation in AutoML.
  • Developed techniques to enhance imputation and improve model outcomes on incomplete datasets.
  • Collaborated with cross-functional teams to implement automated ML pipelines, improving processing speed and cost-efficiency.
CodePath Org
CodePath Speaker
June 2023-Jan 2024
  • Presented my personal CS journey for CodePath to secure funding from corporate partners.
St. Francis Hospital
Machine Learning Internship
Jan 2023-June 2023
  • Analyzed CT angiograms, cleaned, and labeled data for ML training in a heart calcification study.
  • Employed nnUNet to train a model on clinical data, achieving an 88% Dice score with real data.
  • Developed machine learning models to detect heart disease from CT angiogram data.
Clinical Scholar Program-Medical Research Fellowship
July 2021-July 2022
  • Collaborated with developers and physicians to design a patient database for a multimillion-dollar trial.
  • Led data collection and analysis using cardiac MRI scans to generate insights.

Projects

AWS Hosted Resume Website GitHub
  • Designed, implemented, and maintained a fully functional, cloud-hosted website using AWS services (S3, Lambda, DynamoDB, and CloudFront).
  • Automated code deployment using GitHub Actions, streamlining continuous integration pipeline and site updates.
  • Developed the frontend with HTML, CSS, and JavaScript, while using Python for the backend API, deepening knowledge in cloud infrastructure and web development.
Sign Language Detector GitHub
  • Built a custom hand sign detection model using Python, OpenCV, MediaPipe, and TensorFlow, achieving high recognition accuracy.
  • Optimized dataset parameters to refine model performance, enhancing precision in hand sign recognition.
NYC DOE DashboardGitHub
  • Collected, cleaned, and analyzed large datasets of NYC public school data, including attendance, graduation rates, and demographic trends, sourced from NYC Open Data.
  • Developed interactive dashboards in Tableau with geospatial visualizations, utilizing heatmaps and color-coded district maps to display demographic and socioeconomic patterns.
  • Enabled filtering by ZIP code and school, providing detailed insights through bar graphs, line graphs, and tables covering key metrics like enrollment, attendance, and graduation rates (2012-2018).
Heart Disease ClassificationGitHub
  • Applied supervised machine learning models to classify heart disease, using Scikit-learn and TensorFlow for model training and evaluation.
  • Optimized feature selection and improved model performance, leading to an increase in classification accuracy.