Skip to content
View andreyestevam's full-sized avatar
🎯
Coding & Learning
🎯
Coding & Learning

Highlights

  • Pro

Block or report andreyestevam

Block user

Prevent this user from interacting with your repositories and sending you notifications. Learn more about blocking users.

You must be logged in to block users.

Maximum 250 characters. Please don't include any personal information such as legal names or email addresses. Markdown supported. This note will be visible to only you.
Report abuse

Contact GitHub support about this user’s behavior. Learn more about reporting abuse.

Report abuse
andreyestevam/README.md

Andrey Estevam Seabra

Computer Science, Mathematics, Data Science and Statistics student at the University of Richmond (GPA: 3.89). Selected as a Richmond Scholar, one of 25 recipients selected from +12,500 applicants for the university's most prestigious merit award (full-ride, covering full tuition, housing, and food). My work spans robotics systems, full-stack development, and applied machine learning. I'm drawn to problems that require both theoretical rigor and clean, production-ready implementation. Highly interested and curious about turning creative ideas/solutions to real-world problems into computational problems.

Honors

  • Richmond Scholar (Full-Ride; 11,500+ applicants)
  • International STEM Medalist (High School; World's Top 3 Medalist, first Latin American in a major STEM olympiad)
  • Dean’s List
  • All-A’s List
  • Metcalf Prize (5 sophomores awarded)
  • Omicron Delta Kappa (Top 5%)

Some of my experience

Software Engineer, Human and Intelligent Vehicle Ensemble Lab (Aug 2025 – Present)

  • Designed and implemented a revamped application to manage 10+ robot location sensors, replacing a legacy Android/Java system and improving reliability for dozens of users
  • Built a cross-platform Bluetooth management layer in Python by analyzing existing Java Bluetooth code, expanding an Android-only system to support macOS, Windows, and Linux
  • Developed concurrent software using Python Async and multithreading to handle multiple processes, threads, and tasks, enabling real-time visualization of sensor location data

Research Engineer, Human and Intelligent Vehicle Ensemble Lab (May 2024 – Present)

  • Engineered an estimation algorithm for DWM sensor data that increased prediction precision and reduced latency through iterative testing to improve robots' real-time autonomous decision-making
  • Implemented an Unscented Kalman Filter (UKF) for a nonlinear model and automated data-processing pipelines, reducing estimation error from 7.5 cm to 1.6 cm for a 78% improvement while boosting efficiency, and reliability in a high-noise indoor positioning system
  • Designed and developed the estimation algorithm as a ROS2 node, gaining experience with concurrent ROS2 nodes and real-time communication in distributed robotic systems

Skills

  • Programming Skills & Languages: Python, Java, C/ C++, SQL, R, JavaScript, TypeScript, LaTeX, Git, VSCode, Unix, Linux, Github
  • Frameworks, Tools & Technologies: Node. js, Next. js, Express, Flask, Spring Boot, REST APIs, PostgreSQL, SQLite3, MongoDB, Render, React, Tailwind CSS, HTML/ CSS, NumPy, Pandas, Scikit-Learn, Tensorflow, PyTorch, Matplotlib, Beautiful Soup, ROS2

Leadership

  • Vice-President, Association for Computing Machinery (ACM) (Sep 2024 - Present)
  • Vice-President, Robotics Society at the University of Richmond (RobSoc) (Feb 2026 - Present)
  • Lead Software Developer, Robotics Society at the University of Richmond (RobSoc) (Feb 2026 - Present)
  • Richmond Scholars Ambassador, University of Richmond (2024-2025)

🌐 Social and Email:

LinkedIn email

If you’re looking for a driven, creative, and impact-focused problem solver with a strong foundation in both theory and application, let’s connect.

Pinned Loading

  1. stock-price-prediction-recurring-neural-nets stock-price-prediction-recurring-neural-nets Public

    This project builds a stock price prediction model using TensorFlow, Long-Short Term Memory (a specialized type of Recurrent Neural Networks).

    Jupyter Notebook

  2. fullstack-mindmate-ai-therapist-agent fullstack-mindmate-ai-therapist-agent Public

    MindMate AI, Full-stack AI therapy platform with personalized mental health support. Features 24/7 AI-powered sessions using Gemini AI, mood tracking, anxiety relief games, secure authentication, a…

    TypeScript 1

  3. epl-ml-match-winner-prediction epl-ml-match-winner-prediction Public

    End-to-end ML project predicting English Premier League match winners. Scrapes historical match data, cleans and processes it with pandas, then trains a Random Forest model. Includes performance ev…

    Jupyter Notebook

  4. LabHelperDiscordBot LabHelperDiscordBot Public

    LabHelper, a Discord bot for organizing meetings, reminders, and shared resources in research labs (or organizations in general).

    Python 1

  5. handwritten_digit_rec_neuralnets handwritten_digit_rec_neuralnets Public

    Classic ML and CV problem. Recognizes handwritten digits (0 through 9) from images or scanned documents.

    Jupyter Notebook