- 🔭 Currently working on Agentic AI & RAG Systems
- 🌱 Learning LLMs, LangGraph, Multi-Agent Systems
- 💻 AI/ML Engineering Intern
- 🧠 Interested in Production AI Systems
- ⚡ Goal: Become a world-class AI Engineer
High-performance Retrieval-Augmented Generation (RAG) pipeline focused on fast semantic retrieval and efficient LLM responses.
- Semantic search pipeline
- Vector database integration
- Fast embedding generation
- Modular RAG architecture
- Optimized retrieval workflow
Python FastRAG ChromaDB FastEmbed LLMs
🔗 Repo: https://github.com/Bhargav263/FlashRAG
Content-based movie recommendation engine using NLP and cosine similarity.
- Similar movie recommendations
- NLP-based matching
- Streamlit UI
Python Pandas Scikit-learn Streamlit
🔗 Repo: https://github.com/Bhargav263/Movie-Recommendation-System
Deep learning text generation model using sequence prediction with LSTM architecture.
- Sequential text generation
- Deep learning workflow
- Neural language modeling
TensorFlow Keras Deep Learning
🔗 Repo: https://github.com/Bhargav263/LSTMTextGen
Machine learning system for predicting rainfall using historical weather data.
- Feature engineering
- Data preprocessing
- Predictive ML model
Python Scikit-learn Pandas
🔗 Repo: https://github.com/Bhargav263/Rain-Prediction
- Agentic AI
- RAG Pipelines
- LangGraph
- Vector Databases
- LLM Fine-Tuning
- AI System Design
- FastAPI Backend Development
class Bhargav:
def __init__(self):
self.role = "AI Engineer"
self.focus = [
"LLMs",
"RAG Systems",
"Agentic AI",
"Production AI"
]
def build(self):
return "AI systems that solve real-world problems"