Skip to content
View Rhabibi1609's full-sized avatar
🫡
🫡
18 followers · 35 following

Achievements

Achievement: QuickdrawAchievement: Pull Shark

Achievements

Achievement: QuickdrawAchievement: Pull Shark

Highlights

  • Pro

Block or report Rhabibi1609

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 is supported. This note will only be visible to you.
Report abuse

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

Report abuse
Rhabibi1609/README.md

👋 Hey, I'm Rayyan Habeeb!

M.S. Computer Science @ University of South Florida
AI Graduate Research Assistant @ USF
Focus on AI Engineering | Software development | Data Engineering
Building AI-powered assistants, retrieval systems, and multimodal applications
Tampa, Florida, United States

About Me

I'm a graduate Computer Science student passionate about building production-grade AI systems that bridge the gap between Large Language Models (LLMs) and real-world utility. My expertise lies in architecting complex retrieval pipelines, voice-first interfaces, and autonomous agentic workflows.

Featured Projects

The VRAI Ecosystem (Virtual Railroad Assistant Instructor)

VRAI-RAG (Backend) Railroad training RAG backend featuring Qdrant+BM25 hybrid search (RRF), GPU-accelerated OCR for technical manuals, domain acronym expansion, and fallback CoT.

ChatUI (Frontend) VRAI's responsive web interface offers interactive AI source citations, real-time backend metrics, and model comparison for retrieval evaluation.

XR Intelligent Assistant XR AI assistant linking a RAG backend for real-time, in-sim guidance. Features hands-free voice interaction powered by Unity Sentis & ONNX for complex operations.

Data Engineering & Automation

F1 Penalty Data ETL Pipeline End-to-end F1 penalty data ETL pipeline. Leverages Selenium to scrape unstructured racing docs and LLMs to parse text into a structured, analysis-ready database.

Other AI & ML Work

  • [Exhibition Winner] Verdure: A Flutter application combining machine learning, computer vision, and AR for smart gardening and plant-health analysis.
  • Roman Urdu → English Translation: NLP research focused on dataset curation and machine translation for low-resource languages.

🌐 Connect With Me

Always exploring new AI ideas and building experimental systems oki.

Pinned Loading

  1. End-to-End_ETL_4_formula-1-penalty-data-using-selenium-and-llms End-to-End_ETL_4_formula-1-penalty-data-using-selenium-and-llms Public

    ETL pipeline to scrape, parse, and analyze 3,500+ F1 penalty documents from the FIA website using Selenium, LangChain, and LLMs (Gemini/Llama)

    Jupyter Notebook

  2. Fairness-Aware-Logistic-Regression-Using-Demographic-Parity-and-Balance-Metrics Fairness-Aware-Logistic-Regression-Using-Demographic-Parity-and-Balance-Metrics Public

    Evaluate and improve fairness in ML models using demographic parity and balance metrics on synthetic data.

    Jupyter Notebook

  3. Cigarette-Detector Cigarette-Detector Public

    An Azure WebApp + CustomVision project for FRT internship // Video Link: https://youtu.be/iTfyIPZ1V-M

    CSS

  4. Verdure Verdure Public

    Flutter project for an app exhibition.

    Dart

  5. CYK-Algo CYK-Algo Public

    CYK parser using dynamic programming to check string membership in CNF grammars. Python-based, efficient defaultdict storage, O(|G| × n³) complexity, with clear file I/O and parse table output.

    Python

  6. Efficient-Polynomial-Multiplication-using-FFT Efficient-Polynomial-Multiplication-using-FFT Public

    Developed an efficient polynomial evaluation and multiplication framework leveraging Fast Fourier Transform (FFT) in Python, reducing computational complexity from O(n²) to O(n log n).

    Python