I'm a Data Scientist who works across the whole lifecycle: understanding the data, engineering features that actually move the metric, building and evaluating models, then taking them to production with MLOps and extending them with Generative AI. I've also trained 20,000+ working professionals and freshers in data science, so I care about work that is reproducible, measured and easy for someone else to pick up.
- 📊 Data Science & ML: statistics, feature engineering, leakage-proof pipelines, calibrated models evaluated in business terms
- ⚙️ MLOps: DVC, MLflow tracking & registry, Prefect orchestration, FastAPI + Docker serving, CI/CD with GitHub Actions, drift monitoring
- 🤖 Generative AI: transformers, embeddings, LangChain, RAG and agentic apps
- 🔭 Right now: writing a 42-article Generative AI Engineer course and a hands-on LangChain apps series
- 📍 New Delhi, India · 🎓 Post Graduate in AI
Free, hands-on courses from Python to production ML and GenAI. Every number in the articles comes from code that was actually run.
| Repository | What's inside | Status |
|---|---|---|
| GenerativeAI-Engineer-Complete-Course | 42 articles in 7 phases: transformers, tokenization, embeddings, attention → LLM APIs, evaluation, fine-tuning → vector DBs, LangChain, RAG, LangGraph agents → deployment & capstones · start at Article 1 |  |
| Build-GenAI-Apps-with-Langchain-Complete | Code and articles for building beginner-to-advanced Generative AI applications with LangChain | |
| Repository | What's inside | Read |
|---|---|---|
| MLOps_Course_End_to_End | 13 articles taking one churn model from notebook to production: Git, DVC, Docker, Flask & FastAPI, MLflow tracking and registry, Prefect, CI/CD with GitHub Actions | Article 0 |
| Feature_Engineering | 10 notebooks on real data. Same model throughout, only the features change: +0.033 ROC-AUC from feature work alone, with six kinds of leakage measured, not just warned about | Article 1 |
| Machine-Learning-Algorithm-Implementations | Linear, Ridge & Lasso regression, decision trees, random forests, association rules, model selection and ML pipelines | notebooks |
🎁 More free resources (roadmaps, notes, books, videos)
- 🗺️ DSML & AI roadmaps
- ✍️ Data science handwritten notes
- 📖 Data science & ML books
- 🎬 Data science videos
- 🐍 Practice Python: BigBinary Academy · CheckiO
