Skip to content
View tarekmasryo's full-sized avatar

Block or report tarekmasryo

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
tarekmasryo/README.md

Tarek Masryo

AI/ML Engineer | PyTorch · FastAPI · Docker | MLOps & Generative AI
Building reliable ML pipelines, scalable MLOps workflows, and practical Generative AI applications.

LinkedIn

Kaggle

HuggingFace


🧑‍💻 About Me

I work across the end-to-end ML lifecycle:

  • Raw data → clean datasets → interactive analytics & Streamlit dashboards
  • ML pipelines: EDA → Feature Engineering → Modeling → Evaluation → Deployment
  • Generative AI & RAG pipelines for real-world knowledge apps
  • MLOps practices with FastAPI, Docker, MLflow, and CI/CD workflows
  • Publishing open datasets, dashboards, and models on Kaggle & Hugging Face

🏆 Highlights

🏅 Kaggle Expert — Datasets + Notebooks
🚀 Built interactive Streamlit dashboards and visual analytics for EV charging and football (end-to-end case studies)
📊 Published analysis-ready datasets across domains: EV infrastructure, football matches, generative AI platforms, and social media trends
⚡ Developed end-to-end ML pipelines (fraud detection, sentiment analysis, survival prediction) with robust evaluation & explainability
🗂️ Organized portfolio into curated GitHub Lists (Sports ⚽, EV ⚡, GenAI 🤖, Social Media 📱) to showcase case studies clearly


🛠️ Core Tech Stack

Category Tools
Languages & Core Python SQL Bash
Frameworks PyTorch TensorFlow Scikit-Learn XGBoost
MLOps / Deployment FastAPI Docker MLflow GitHub Actions

🔧 Extended Skills

Category Tools
Visualization & Apps Streamlit Plotly Matplotlib Seaborn
Databases PostgreSQL MySQL SQLite
Cloud & Storage AWS S3 GCP BigQuery
Generative AI HuggingFace LangChain RAG Apps

📌 Featured Projects

🔹 Credit Card Fraud Detection — Pipeline

End-to-end fraud detection workflow with cost-sensitive thresholds, calibration, and deployment-ready API.

🔹 IMDB Sentiment Analysis (NLP)

EDA + classical ML baselines + BiLSTM model for text classification.

🔹 Healthcare Analytics — Diabetes Prediction

Applied ML models with calibration curves, decision curves, and explainability tools.

🔹 Titanic Survival Prediction — Complete ML Workflow

Feature engineering, model ensembling, and explainability on the classic dataset.


📂 Portfolio Sections (GitHub Lists)


📊 GitHub Stats


🌍 Community & Open Source

  • 🏅 Kaggle Expert — Competitions, Datasets & Notebooks
  • 🚀 HuggingFace Publisher — Datasets, Spaces, and Models
  • GitHub — Open-source ML Pipelines

⭐ Let’s Collaborate

🚀 Always exploring the edge of Machine Learning & Generative AI.

⭐ If you like my work, give the repos a star — it helps more people discover them.

🤝 Open to collaborations, research, and real-world ML applications.

📩 Let’s connect: data, ideas, and pipelines are better when shared.


“Bridging data and deployment — one pipeline at a time. Exploring Generative AI to reimagine what’s possible.”

Pinned Loading

  1. pima-diabetes-pipeline pima-diabetes-pipeline Public

    Jupyter Notebook 9

  2. text-sentiment-analysis text-sentiment-analysis Public

    IMDB-Reviews-EDA-Classical-Models-BiLSTM

    Jupyter Notebook 6

  3. fraud-detection-dashboard fraud-detection-dashboard Public

    fraud-detection-dashboard

    Python 5

  4. cancer-risk-factors-data cancer-risk-factors-data Public

    Clean and well-documented dataset of cancer risk factors for ML & EDA

    4

  5. ev-charging-dashboard ev-charging-dashboard Public

    Global EV Charging Stations with power classes + EV models

    Python 3

  6. genai-tools-data genai-tools-data Public

    Generative AI tools (2025): categories, capabilities, open-source & API

    3