AI/ML student focused on Explainable AI, Machine Learning Engineering, MLOps, and Open-Source Python tools.
I am building my profile through real open-source contributions and practical AI/ML projects that connect model development, explainability, monitoring, and reproducible machine learning workflows.
I opened a bug-fix pull request to SHAP, a widely used explainable AI library.
Contribution: fixed Explanation.cohorts() failing with integer and boolean cohort labels by safely converting non-string cohort keys before passing them into Cohorts(**kwargs).
PR: shap/shap#4816
What this shows:
- Python debugging and bug fixing
- Understanding of SHAP internals
- Regression testing
- Contribution to real-world Explainable AI tooling
I merged a documentation pull request to sktime-mcp, an MCP server that exposes sktime’s time-series machine learning registry and workflows to LLM agents.
Contribution: clarified first-time setup instructions, .venv usage, and MCP client fallback guidance using python -m sktime_mcp.server.
Status: Merged
What this shows:
- Merged open-source documentation contribution
- Agentic AI / MCP ecosystem awareness
- Developer tooling and setup clarity
- Practical understanding of Python environments
Interactive SHAP dashboard for tabular machine learning models using Streamlit, scikit-learn, and SHAP.
Focus areas:
- Global feature importance
- Local prediction explanations
- Random Forest classification
- Explainable AI dashboard design
Repository: https://github.com/Abdo-ateM/model-explainability-dashboard
Lightweight ML monitoring dashboard for tracking model performance, prediction drift, and feature distribution changes.
Focus areas:
- Model evaluation
- Feature drift detection
- Simulated production data
- Streamlit monitoring dashboard
- Practical MLOps concepts
Repository: https://github.com/Abdo-ateM/ml-model-monitoring-dashboard
End-to-end machine learning pipeline for Adult Income classification using scikit-learn, ColumnTransformer, cross-validation, and model evaluation.
Focus areas:
- Tabular data preprocessing
- Classification modeling
- Logistic Regression and Random Forest
- Cross-validation
- Saved evaluation artifacts
Repository: https://github.com/Abdo-ateM/adult-income-ml-pipeline
Research-style comparison of regularization techniques in neural networks using TensorFlow/Keras and MNIST.
Techniques compared:
- L1 Regularization
- L2 Regularization
- Dropout
- Batch Normalization
- Elastic Net
Repository: https://github.com/Abdo-ateM/machine-learning-regularization-comparison
Deep learning video colorization pipeline using MobileNetV2 U-Net, TensorFlow/Keras, OpenCV, LAB color space, and FFmpeg.
Focus areas:
- Computer vision
- Deep learning pipeline design
- Frame-by-frame video processing
- Image color space transformation
Repository: https://github.com/Abdo-ateM/video-colorization-deep-learning
Languages: Python, C++, Java, SQL
Machine Learning: scikit-learn, TensorFlow/Keras, SHAP, model evaluation, feature engineering, neural networks
Data: pandas, NumPy, matplotlib, seaborn, preprocessing pipelines, cross-validation
MLOps / Engineering: Streamlit, Git, GitHub, virtual environments, reproducible project structure, model monitoring basics
Open Source: pull requests, issue discussion, regression tests, documentation improvement
- Explainable AI and model interpretability
- Open-source AI/ML tools
- Agentic AI and MCP-based workflows
- Practical machine learning engineering
- Model monitoring and evaluation
- Healthcare AI and real-world ML applications
GitHub: https://github.com/Abdo-ateM
Email: abdelgalilabdelrahman0@gmail.com