I’m Ragiri Himadeep, a self-taught AI/ML Engineer and graduate in BBA – Business Analytics. Despite not holding a traditional Computer Science degree, I have rigorously mastered Artificial Intelligence, Machine Learning, and MLOps through countless hours of hands-on practice, online courses, and real-world projects.
Driven by relentless curiosity and ambition, I’ve built production-ready, end-to-end systems across domains like Machine Learning, Deep Learning, Natural Language Processing, and Cloud-based MLOps. My portfolio reflects:
- Practical expertise,
- Industry-level implementation,
- And a passion for solving complex, high-impact problems with technology.
Every project here is designed not just to demonstrate skill — but to solve real challenges with scalable, maintainable AI systems.
- 🙋♂️ About Me
- 🚀 Production-Ready AI Systems
- 📊 Machine Learning Projects
- 🧠 Deep Learning Projects
- 📝 Natural Language Processing (NLP) Projects
- 🧰 Technologies & Skills
- 🏆 Certifications & Achievements
- 🗺️ Future Goals
- 📬 Let’s Connect
I’m a BBA Business Analytics graduate with a relentless passion for AI and Machine Learning. Self-taught from the ground up, I’ve transitioned from business analytics to building production-ready AI systems that solve real-world problems. My journey reflects resilience, curiosity, and a commitment to excellence in AI/ML engineering. I specialize in end-to-end ML pipelines, cloud deployments, and cutting-edge NLP and deep learning solutions. My goal is to create scalable AI systems that drive business impact and innovation.
These projects showcase my ability to build scalable, production-grade AI systems with robust MLOps pipelines and cloud integration.
🔹 ResmoAI
AI-Powered Resume Platform
A full-stack platform for resume creation, resume optimization, job match scoring, and instant feedback. Built with Next.js, FastAPI, Firebase (Auth, Firestore, Storage), Docker and Google Cloud Run. Features PDF generation, CI/CD via GitHub Actions, and scalable deployment.
Impact: Empowers users to create and optimize ATS-friendly resumes, enhancing job application success through AI-driven formatting and keyword optimization.
End-to-End MLOps Pipeline
Automates the ML lifecycle for telecom churn prediction using ZenML, MLflow, GitHub Actions, Docker, and AWS EC2. Includes data ingestion, model training, registry, drift detection, retraining, and DynamoDB integration.
Impact: Ensures continuous model performance with automated retraining and monitoring.
ETL + Sentiment Analytics + Dashboard
A production-grade pipeline using Apache Airflow, Spark, Firebase, and Streamlit. Ingests, analyzes, and visualizes e-commerce review sentiments in real time. Fully containerized with Docker.
Impact: Delivers actionable insights for e-commerce platforms with real-time dashboards.
These projects demonstrate my expertise in classical machine learning, feature engineering, and model evaluation.
| Project | Description | Technologies |
|---|---|---|
| Wine Classification | KNN classifier on the Wine dataset with evaluation and visual analysis. | Scikit-learn, Matplotlib |
| UNSW-NB15 Network Intrusion Detection | Random Forest for intrusion detection with extensive preprocessing and feature selection. | Scikit-learn, Pandas |
| Spam Email Classification | Logistic regression + TF-IDF for accurate spam detection. | Scikit-learn, TF-IDF |
| Sentiment Analysis on IMDB | Naive Bayes classifier with GridSearchCV and TF-IDF. | Scikit-learn, TF-IDF |
| Movie Recommendation System | Content-based recommender using TF-IDF and cosine similarity. | Scikit-learn, Pandas |
| Instacart Market Basket Analysis | Collaborative filtering + TruncatedSVD to recommend grocery items. | Scikit-learn, NumPy |
| Housing Price Prediction | Linear and Random Forest regression with performance evaluation. | Scikit-learn, Pandas |
| Gold Price Prediction | Historical gold price regression using Random Forest. | Scikit-learn, Pandas |
| Diabetes Prediction | SVM model trained on patient data. | Scikit-learn |
| Customer Segmentation | K-Means clustering for marketing insights. | Scikit-learn, Seaborn |
| Credit Card Fraud Detection | Logistic regression on imbalanced fraud dataset. | Scikit-learn, Pandas |
| Big Mart Sales Prediction | XGBoost regression to forecast sales. | XGBoost, Pandas |
| Airbnb New User Bookings | Predicts user destinations using XGBoost and Logistic Regression. | XGBoost, Scikit-learn |
These projects highlight my expertise in neural networks, computer vision, and reinforcement learning.
| Project | Description | Technologies |
|---|---|---|
| Face Recognition System | Real-time face recognition via OpenCV + Flask with JSON storage. | OpenCV, Flask, PyTorch |
| Dog Breed Classifier | ResNet50 model with PyTorch and Flask deployment. | PyTorch, Flask, ResNet50 |
| Self-Driving Car RL | Deep reinforcement learning using PPO + Gymnasium. | Stable-Baselines3, Gymnasium |
| DL Movie Recommendation System | Neural matrix factorization on MovieLens with PyTorch. | PyTorch, MovieLens |
| Credit Risk Scoring System | Neural network to classify credit risk with PyTorch. | PyTorch, Pandas |
| Bike Helmet Detection | YOLOv11 real-time detection system, deployed with Flask + Ngrok. | YOLOv11, Flask, Ngrok |
| Anime Face Generation GAN | DCGAN for anime face generation + interactive web app. | PyTorch, DCGAN, Flask |
These projects showcase my expertise in advanced NLP techniques, transformers, and LLMs.
| Project | Description | Technologies |
|---|---|---|
| Image Captioning | CNN-LSTM model using ResNet18 + GloVe on Flickr8k. | PyTorch, ResNet18, GloVe |
| Transformer from Scratch | Custom Transformer implementation in PyTorch. | PyTorch, Transformers |
| GPT from Scratch | Educational GPT model showcasing core transformer blocks. | PyTorch, Transformers |
| RAG-Chatbot | Retrieval-Augmented QA with PDFs using IBM Watsonx + LangChain. | LangChain, IBM Watsonx |
| BiLSTM NER | Named Entity Recognition with Flask UI on CoNLL-2003. | PyTorch, Flask, BiLSTM |
| Multi-Agent Data Analysis | Mistral-7B agents automate full data analysis pipeline. | Mistral-7B, LangChain |
| BERT Emotion Detection | Text classification using fine-tuned BERT model. | Hugging Face, BERT |
| Advanced RAG Chatbot | Multi-source knowledge chatbot (PDFs, YouTube, Wiki). | LangChain, ChromaDB |
| Abstractive Headline Gen with BART | LoRA-tuned BART for news summarization. | Hugging Face, BART, LoRA |
| AI Code Doc Generator | GPT-2 based tool for Python docstring generation. | GPT-2, Hugging Face |
- Cloud Platforms: AWS (EC2, DynamoDB), Google Cloud Platform (GCP, Cloud Run)
- Containerization: Docker, Kubernetes
- CI/CD: GitHub Actions
- MLOps Tools: MLflow, ZenML
- Data Pipelines: Apache Airflow, Apache Spark
- Database: Firebase (Firestore, Auth, Storage)
- Frameworks: Scikit-learn, XGBoost
- Data Processing: Pandas, NumPy
- Visualization: Seaborn, Matplotlib
- Techniques: TF-IDF, Cosine Similarity, PCA, SVM, Feature Engineering, GridSearchCV, EDA
- Frameworks: PyTorch, TensorFlow, Keras
- Architectures: CNNs, RNNs, LSTMs, GANs, Embeddings
- Techniques: Transfer Learning (ResNet, BERT), Stable-Baselines3 (RL)
- Libraries: Hugging Face Transformers, LangChain, ChromaDB
- Models: BERT, GPT-2, BART
- Techniques: Tokenization, Attention Mechanisms, Named Entity Recognition (NER), PEFT, LoRA
- Backend: FastAPI, Flask
- Frontend: Streamlit, Gradio, Next.js (React), HTML/CSS/JS (basic)
- Deployment: Ngrok, RESTful APIs
- Tools: Docker, GitHub Actions
- Processes: CI/CD workflows, model versioning, monitoring
- Data Engineering (ETL pipelines)
- Recommender Systems
- Exploratory Data Analysis (EDA)
- Real-time ML applications
-
Machine Learning Specialization – Stanford Online & DeepLearning.AI (Coursera) Completed under Prof. Andrew Ng, covering supervised learning, regression, classification, and ML engineering practices.
-
Deep Learning Specialization – DeepLearning.AI (Coursera) Mastered neural networks, CNNs, RNNs, LSTMs, and sequence models, taught by Andrew Ng.
-
IBM Generative AI Engineering Professional Certificate – IBM (Coursera) Gained hands-on experience in building and deploying generative AI applications using foundational models, prompt engineering, and enterprise AI tools.
-
Continuously upskilling through top-tier online platforms like Coursera, Udemy, etc.
-
Actively contributing to real-world projects, open-source tools, and scalable AI systems.
- 🧠 Advance my expertise in deep learning, generative AI, and large language models.
- 🏗️ Build a full-stack, production-grade AI product that solves real-world problems.
- 🏢 Launch my own AI startup focused on empowering users with intelligent tools.
- 🌍 Contribute to open-source AI research and collaborate with global talent.
- 🎓 Pursue continued education in economics, neuroscience, and philosophy to build interdisciplinary innovation.
I’m actively seeking full-time roles and internships in AI/ML Engineering and Applied Data Science. My projects demonstrate my ability to deliver production-ready AI solutions, and I’m excited to contribute to innovative teams. Reach out to me:
- 📧 Email: himadeepragiri@gmail.com
- 🔗 LinkedIn: Ragiri Himadeep
- 🐙 GitHub: https://github.com/HimadeepRagiri
- 🌐 Portfolio Website: [Coming Soon]