This repository documents my personal journey into Machine Learning Engineering.
It is both a study log and a portfolio showcase, highlighting everything I learn from the foundations of ML to production-grade MLOps practices.
Inside you’ll find:
- 📖 Concept summaries explained in detail
- 💻 Code snippets & experiments to reinforce learning
- 🚀 Projects & exercises demonstrating end-to-end ML workflows
- Module 1: Introduction to Machine Learning
- Module 2: Machine Learning for Regression
- Module 3: Machine Learning for Classification
- Module 4: Evaluation Metrics & Validation
- Module 5: Deploying Machine Learning Models
- Module 6: Decision Trees & Ensemble Learning
- Module 7: Neural Networks & Deep Learning
- Module 8: Serverless Deep Learning
- Module 9: Kubernetes & TensorFlow Serving
- Module 1: Introduction to AI and Machine Learning on Google Cloud
- Module 2: Prepare Data for ML APIs on Google Cloud
- Module 3: Working with Notebooks in Vertex AI
- Module 4: Create ML Models with BigQuery ML
- Module 5: Engineer Data for Predictive Modeling with BigQuery ML
- Module 6: Feature Engineering
- Module 7: Build, Train and Deploy ML Models with Keras on Google Cloud
- Module 8: Production Machine Learning Systems
- Module 9: Machine Learning Operations (MLOps): Getting Started
- Module 10: Machine Learning Operations (MLOps) with Vertex AI: Manage Features
- Module 11: Introduction to Generative AI
- Module 12: Introduction to Large Language Models
- Module 13: Machine Learning Operations (MLOps) for Generative AI
- Module 14: Machine Learning Operations (MLOps) with Vertex AI: Model Evaluation
- Module 15: Build and Deploy Machine Learning Solutions on Vertex AI
- Module 16: Create Generative AI Apps on Google Cloud
As I progress, I’ll work with an evolving ML engineering stack, including:
- Programming & ML: Python, NumPy, Pandas, Scikit-Learn, TensorFlow, PyTorch
- Deployment & MLOps: Docker, Kubernetes, Flask/FastAPI, AWS Lambda
- Develop solid Machine Learning Engineering skills
- Document learnings in a way that serves as a public portfolio
- Build & deploy real-world ML projects end-to-end
- Share my knowledge and progress with the community
- Machine Learning Zoomcamp by DataTalks.Club
- Machine Learning Engineer Learning Path by Google Cloud