CS Final Year Student at VIT-AP University building production-ready AI/ML systems. Currently completing a 120-day zero-to-job-ready ML Engineering roadmap.
- End-to-end ML pipelines — from raw data to deployed APIs
- RAG systems using LangChain, FAISS, and Groq LLMs
- Computer Vision models with PyTorch and HuggingFace
- Production MLOps pipelines with Docker, MLflow, and Evidently
| Project | What it does | Stack | Demo |
|---|---|---|---|
| PDF Chatbot | Chat with any PDF using RAG | LangChain, FAISS, Groq, Streamlit | — |
| Fake News Detector | Classifies news as FAKE or REAL | DistilBERT, HuggingFace, Gradio | Try it |
| MLOps Pipeline | Full train→deploy→monitor pipeline | FastAPI, Docker, MLflow, Evidently | Live API |
| Sentiment Classifier | IMDB review sentiment analysis | PyTorch, GRU, HuggingFace | — |
| LSTM Time Series | Sequence prediction with LSTM | PyTorch, LSTM | — |
ML/DL: PyTorch · Scikit-learn · HuggingFace · LangChain · FAISS
MLOps: Docker · FastAPI · MLflow · DVC · Evidently · GitHub Actions
LLMs: Groq · LLaMA 3 · DistilBERT · RAG pipelines
Data: Pandas · NumPy · Matplotlib · Seaborn
Deploy: Render · HuggingFace Spaces · Streamlit Cloud
- ✅ Phase 1-5 complete — Classical ML → Deep Learning → NLP → LLMs → MLOps
- 🔄 Phase 6 in progress — Portfolio + Kaggle + Job Applications
- 🎯 Target: AI/ML Engineer role, 10+ LPA
