I’m an AI ML Engineer focused on building production-grade Generative AI systems — from LLM-powered chatbots to retrieval-augmented and agentic workflows — backed by strong software engineering fundamentals.

Currently, I contribute to the IndiGo AI Chatbot, where I design and deploy LLM-driven conversational systems using Python, FastAPI, Azure OpenAI, Redis, and RAG architectures to support real-time, high-scale customer interactions.

💡 My work sits at the intersection of AI system design and backend engineering — ensuring AI solutions are accurate, scalable, observable, and reliable.

• 🎓 Education
  B.Tech — Computer Science & Engineering
  Specialization: Artificial Intelligence & Machine Learning

• 🌐 Portfolio & Work

  

• 🧠 Current Focus

  • Designing and optimizing LLM-based applications
  • Building RAG pipelines with vector search and document intelligence
  • Developing agentic AI systems using LangChain, LangGraph, and MCP Server
  • Productionizing AI workflows with FastAPI, Redis, and Azure

• 📬 Connect with Me

  

LLMs • RAG • Agentic AI • LangChain • LangGraph • Prompt Engineering • NLP • Embeddings • Vector Search

🚀 Developing and scaling IndiGo’s AI-powered chatbot platform

• LLM orchestration using Azure OpenAI
• High-accuracy RAG pipelines with Azure Cognitive Search
• Prompt engineering and intent routing for real-world queries
• Backend services with FastAPI and Redis caching
• Secure API integrations and cloud deployment on Microsoft Azure

Focused on accuracy, latency, scalability, and production reliability.

• 🚀 Enhancing the IndiGo AI Chatbot backend with scalable and robust architecture
• 🧠 Exploring RAG, LangChain, and LLMOps for context-aware chat automation
• ☁️ Strengthening skills in Azure, Docker, and microservice deployments
• 💻 Building full-stack projects and contributing to open-source

✨ "Code. Learn. Build. Repeat."
🌟 Always exploring how AI and software engineering can create real-world impact.