Skip to content
View devangdhyani's full-sized avatar

Highlights

  • Pro

Block or report devangdhyani

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
devangdhyani/README.md

Devang Dhyani — AI Engineer (Generative AI | RAG | LLMOps)

AI Engineer focused on Generative AI, Retrieval-Augmented Generation (RAG), MCP integration patterns, agentic AI, and multi-agent systems. I design, build, and deploy production-lean generative AI solutions and automation pipelines.


What I do

  • Build end-to-end GenAI systems: RAG pipelines, LLM orchestration, and agentic workflows.
  • Operate and deploy models using LLMOps and MCP-style integrations.
  • Automate CI/CD for model + infrastructure deployments (Azure-focused).

Highlight

RAG Medical Chatbot — A production-lean RAG system for medical Q&A with secure Azure VM deployment, ACR-based containerization, NSG configuration, and GitHub Actions CI/CD.

Core skills & technologies

  • Generative AI, Retrieval-Augmented Generation (RAG)
  • Prompt engineering, LLM orchestration, agentic AI, multi-agent systems
  • LLMOps, MCP patterns, production deployment
  • Azure (VM, ACR, NSG) • CI/CD automation
  • Python, Docker, REST APIs, Vector databases

Selected project

  • RAG Medical Chatbot — Production-lean RAG stack for medical Q&A with Azure VM deployment, ACR container images, NSG network controls, Pinecone/VectorDB indexing, and GitHub Actions CI/CD.

Contact

Open to

  • Collaboration on GenAI / RAG / multi-agent projects
  • Contract or full-time roles in LLMOps and production AI engineering

Pinned Loading

  1. it-auto-Git it-auto-Git Public

    1