// Generative AI Engineer, RAG & Agentic AI Developer

Urmila Saini

Description

Urmila Saini builds useful AI systems with RAG, agentic workflows, Model Context Protocol, LangGraph, Python, FastAPI, vector search, and production-minded LLM application design.

View Projects Download Resume
Animated character illustration of Urmila Saini
@urmila.ai
--:-- -

Lucknow, India

Generative AI Engineer

Open to opportunities 5+ apps shipped
Animated portrait of Urmila Saini

Urmila Saini

Generative AI Engineer

Lucknow, India

01 - ABOUT ME

Building AI systems
that do not just answer,
but act.

I design and build intelligent systems that retrieve the right context, reason over it, and take action. My work blends RAG, agents, MCP workflows, and production Python to ship real-world AI products people can actually use.

5+AI Apps ShippedProduction Ready
1+Years LearningAI & ML
1000+Hours of CodeSolving Problems
AlwaysCuriousAlways Learning

My Education Journey

2025 - Present

M.Sc. Data Science

IIIT Lucknow

Specializing in Gen AI, Data Science and Intelligent Systems.

2021 - 2024

B.Sc. Mathematics

University of Rajasthan

Built a strong foundation in mathematics and problem solving.

What I Work On

RAG Systems

Building retrieval pipelines that understand and deliver the right context.

Agentic AI

Designing workflows that plan, reason, and execute tasks autonomously.

MCP Workflows

Orchestrating tools and function calls through Model Context Protocol.

AI Applications

Shipping real-world apps that solve problems and create impact.

Current FocusBuilding scalable, reliable, and user-centric AI products.

02 - Experience

Where I've Been Working

Sep 2025 - Present

Data Science Intern

Climate Reservation Observatory (CRO)

  • Built predictive analytics pipelines in Python and SQL to forecast climate-risk indicators from environmental datasets.
  • Owned preprocessing, feature engineering, experimentation, and model evaluation across machine learning and deep learning workflows.
  • Translated forecasting outputs into actionable climate-risk insights for decision-making.
2025 - Present

Teaching Assistant

IIIT Lucknow

  • Mentor students on Machine Learning, Deep Learning, Python, and Data Science coursework through conceptual and implementation support.

03 - Expertise

AI Engineering Focus Areas

Generative AI Engineer

Generative AI Engineer Building Practical LLM Applications

Urmila Saini is a Generative AI Engineer building RAG systems, agentic AI workflows, MCP tools, Python APIs, FastAPI backends, and production-minded LLM applications.

Generative AI EngineerLLM ApplicationsPython AI EngineerFastAPI AI Apps
Explore Focus->

RAG Developer

RAG Developer for Retrieval-Augmented Generation Systems

Urmila Saini builds retrieval-augmented generation systems with OCR, embeddings, vector search, semantic retrieval, and grounded LLM answers.

RAG DeveloperRetrieval-Augmented GenerationVector SearchEmbeddings
Explore Focus->

Agentic AI Developer

Agentic AI Developer for Tool-Using LLM Workflows

Urmila Saini builds agentic AI workflows with LangGraph, Model Context Protocol, multi-agent orchestration, tool calling, and real-time data integrations.

Agentic AI DeveloperMCP WorkflowsLangGraphMulti-Agent AI
Explore Focus->

04 - Projects

AI Projects I've Shipped

Saarthi AI project preview Live Space

Saarthi AI

Agentic Commute Intelligence Platform

Saarthi AI predicts commute risk using live traffic, weather, events, and route signals with an explainable departure recommendation.

  • Built an agentic platform that estimates lateness risk and recommends optimal departure times.
  • Integrated live traffic, weather, events, route-risk signals, and MongoDB Atlas state.
MCPMulti-AgentMongoDB AtlasLive APIsAgentic AI
Case Study-> View Code->
SmartNotes AI project preview Static preview

SmartNotes AI

Handwritten Notes RAG Assistant

SmartNotes AI turns handwritten notes into a searchable study assistant using OCR, embeddings, retrieval, and AI summaries.

  • Built a RAG assistant that turns photographed handwritten notes into a searchable knowledge base.
  • Engineered chunking, indexing, and vector retrieval to keep responses grounded.
RAGOCREmbeddingsVector SearchLLM Apps
Case Study-> View Code->
MediSwap project preview Live Space

MediSwap

Semantic Medicine Recommendation System

MediSwap finds composition-based medicine alternatives with fuzzy matching, semantic search, FastAPI, Qdrant, and embeddings.

  • Built a medicine recommendation platform for composition-based alternatives.
  • Combined fuzzy string matching with vector similarity over BGE embeddings.
FastAPIQdrantBGE EmbeddingsRapidFuzzSemantic Search
Case Study-> View Code->

// MY EXPERTISE

Skills That Build Intelligent Solutions

I combine AI innovation with full-stack development to build powerful, scalable and user-centric products.

AI & LLMs

  • Large Language Models
  • Prompt Engineering
  • Fine-Tuning
  • Model Evaluation
  • Gemini / OpenAI API
Expert95%

RAG & Retrieval

  • RAG Architecture
  • Vector Databases
  • Hybrid Search
  • Re-ranking
  • Context Optimization
Expert95%

Agents & Automation

  • LangGraph
  • Multi-Agent Systems
  • MCP Workflows
  • Tool Calling
  • Agent Orchestration
Advanced90%

Backend Development

  • Python
  • FastAPI
  • REST APIs
  • Async Programming
  • API Authentication
Advanced90%

Databases & Storage

  • MongoDB
  • ChromaDB
  • FAISS
  • SQLite / DuckDB
  • Data Modeling
Advanced88%

MLOps & Deployment

  • Docker
  • Hugging Face Spaces
  • API Deployment
  • Git & GitHub
  • Model Serving
Advanced88%

</> TECH ARSENAL

Python logo

Python

FastAPI logo

FastAPI

LA

LangGraph

CH

ChromaDB

MongoDB logo

MongoDB

Gemini logo

Gemini

OpenAI logo

OpenAI

Git logo

Git

Docker logo

Docker

Hugging Face logo

Hugging Face

Always Building. Always Learning.

20+Projects
1+Years
1000+Hours of Code
AlwaysCurious

06 - Credentials

Certifications & Achievements

Certifications

  • Anthropic - Model Context Protocol (MCP): Advanced Topics
  • LangChain Academy - Introduction to LangGraph (Python)
  • Google Cloud Skills Boost - Introduction to Generative AI

Achievements

  • Deployed 5+ AI and Generative AI applications on Hugging Face Spaces.
  • Participated in the Google Cloud Rapid Agent Hackathon.

07 - FAQ

Quick Facts for Recruiters and Search

Who is Urmila Saini?

Urmila Saini is a Generative AI Engineer based in Lucknow, India, focused on RAG systems, agentic AI workflows, MCP tooling, Python backends, FastAPI, vector search, and LLM applications.

What does Urmila Saini build?

She builds AI applications such as RAG assistants, agentic workflow systems, semantic search tools, and production-minded Python APIs.

Which projects best show Urmila Saini's AI engineering work?

Saarthi AI shows agentic AI and MCP workflow skills, SmartNotes AI shows RAG and OCR-based retrieval, and MediSwap shows semantic search with FastAPI, Qdrant, embeddings, and fuzzy matching.

08 - Contact

Let's Build Something

Have a role, a project, or a question about agentic RAG systems? My inbox is open.

urmilasaini067@gmail.com +919251062561
GitHub -> LinkedIn -> Hugging Face -> Kaggle ->