Skip to content
View 21f3001527's full-sized avatar

Block or report 21f3001527

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
21f3001527/README.md

👋 Hi, I'm Rajeev Kumar

Typing SVG

🎓 BS Data Science & ApplicationsIIT Madras (Graduated May 2026) 🤖 Building production ML and AI systems — MLOps pipelines, REST APIs, GenAI applications 🔍 Open to Data Science / Data Engineer / ML Engineer / AI Engineer roles

LinkedIn GitHub Email Profile Views


🧠 Tech Stack

🤖 AI / GenAI

LLMs HuggingFace LangChain RAG Prompt Engineering Vector Search LoRA/PEFT Transformers

📊 Machine Learning & Data Science

Scikit-learn XGBoost LightGBM PyTorch Pandas NumPy Matplotlib Seaborn

⚙️ MLOps & Deployment

MLflow FastAPI Docker GitHub Actions SHAP Evidently

🗄️ Data Engineering

SQL MySQL SQLite Redis Celery

🛠️ Tools & Platforms

Python Linux Git Google Colab Kaggle Flask Vue.js


🚀 Projects

🔍 CrimeCast: Crime Category Prediction

Python Scikit-learn Pandas NumPy Matplotlib Seaborn

  • Trained 4 classifiers (Random Forest, SVC, AdaBoost, Decision Tree) on LAPD crime data — Random Forest was the best performer
  • Engineered time-based, geographic, and demographic features; applied GridSearchCV hyperparameter tuning
  • Conducted feature importance analysis to identify key predictors across location, timing, and incident type

🔧 MLOps Pipeline: Explainability, Fairness & Drift Monitoring

MLflow SHAP GitHub Actions Scikit-learn Evidently

  • Built an end-to-end ML observability pipeline with SHAP explainability across demographic groups and data drift detection (KS, PSI tests) triggering automated retraining alerts
  • Automated the full pipeline (train → evaluate → explain → monitor) via GitHub Actions CI, cutting manual intervention to zero
  • Integrated MLflow for experiment tracking, model registry, and reproducibility

🌐 Student Management System – REST API

FastAPI SQLite JWT SQLModel Uvicorn Railway

A production-deployed REST API for managing students, courses, enrollments, and grades with JWT-based authentication.

  • Built full CRUD routes for Students, Courses, Enrollments, and Grades using FastAPI with auto-generated Swagger docs at /docs
  • Implemented JWT authentication (python-jose + passlib/bcrypt) — all routes are protected and require a valid token
  • Used SQLModel (Pydantic + SQLAlchemy) for ORM, with duplicate checks for emails, course codes, and enrollments; marks validated between 0–100
  • Deployed live on Railway with a Procfile + Uvicorn ASGI server

Live Demo


📊 Business Data Management – 99 Market Mall Case Study

Python SQL Pandas Matplotlib Tableau Excel

  • Analyzed sales and inventory data for a retail mall (~₹2,00,000/month revenue) to identify operational gaps
  • Identified top product categories contributing ~70% of total sales via Pareto analysis; surfaced seasonal trends (November peak, January low)
  • Delivered 6 actionable recommendations projected to reduce capital blockage by 20–25%

🧠 Quiz Master V1 & V2 – Full Stack Web App

Flask Vue.js Redis Celery SQLite Bootstrap

  • Built a multi-role quiz platform (V1) with admin and user roles, quiz creation, scoring, and result analytics
  • Extended to V2 with REST API, Vue.js frontend, Celery background jobs, and interactive performance dashboards

📈 GitHub Stats


🎓 Education & Certifications

🎓 BS Data Science & Applications — IIT Madras (2021–2026, CGPA: 8.1)

Workshops — IIT Madras

Workshop Focus
Mathematical Foundations for ML Linear algebra, probability, optimization
Machine Learning Techniques Supervised & unsupervised learning
Deep Learning & NLP (Prof. Mitesh Khapra / AI4Bharat) Neural networks, transformers, NLP
Understanding Google Cloud Platform GCP, BigQuery, Vertex AI
NumPy and Pandas Workshop Data manipulation from scratch

Certifications

  • 📜 Mathematics - Basics to Advanced for Data Science and GenAI — Udemy
  • 📜 Python for Data Science & AI — Coursera
  • 📜 Intro to Git and GitHub — Coursera
  • 📜 SQL (Basic, Intermediate) — HackerRank

📫 Let's Connect

📧 Email rajeev90767@gmail.com
💼 LinkedIn linkedin.com/in/rajeev245
🐙 GitHub github.com/21f3001527
📍 Location Patna, Bihar, India
📞 Phone +91 7903766709

"Ship real systems. Learn by building."

Pinned Loading

  1. AI-Ticket-Triage-System AI-Ticket-Triage-System Public

    AI powered support ticket triage system classifies, prioritizes, and drafts replies for customer tickets using Gemini 2.5 Flash + FastAPI + Streamlit.

    Python 1

  2. dpf-soot-predictor dpf-soot-predictor Public

    🚛 Predictive maintenance pipeline for Diesel Particulate Filters RF/XGBoost models (R² 0.9997), FastAPI serving, MLflow tracking, Dockerized, CI-tested.

    Python

  3. ai-travel-itinerary-generator ai-travel-itinerary-generator Public

    An end-to-end no-code automation that turns a simple form submission into a personalized, AI-generated travel itinerary — complete with real weather data, restaurant picks, and a polished PDF deliv…

  4. medical-noshow-prediction medical-noshow-prediction Public

    Production-ready machine learning pipeline for predicting medical appointment no-shows using LightGBM, FastAPI, MLflow, Docker, and CI/CD.

    Jupyter Notebook

  5. multilingual-sentiment-analysis multilingual-sentiment-analysis Public

    Multilingual sentiment classification across 13 Indian languages using Gemma 3 1B-IT

    Jupyter Notebook

  6. Recall Recall Public

    AI study companion that turns PDF notes into summaries, quizzes, flashcards, and a chat assistant with memory — powered by LangChain, ChromaDB, and Groq.

    Python