Hi, I'm Preksha ๐Ÿ‘‹

I build intelligent systems that actually work.

AI Engineer ยท RAG & Agentic Workflows

Based in

Indore, India

Status

Open to work

See my work โ†’
Illustrated portrait of Preksha Barjatya wearing round sunglasses

B.Tech CSE (AI & ML)

2023โ€“27

01.

About Me

I'm Preksha Barjatya, a B.Tech CSE (AI & ML) student at Acropolis Institute of Technology and Research, Indore (affiliated to RGPV Bhopal), graduating in 2027.

I build Retrieval-Augmented Generation (RAG) applications, FastAPI-based AI solutions, data pipelines, and SQL-driven analytics systems โ€” turning language models into dependable, production-ready tools.

Currently interning as an AI Engineer at Santerra Hygiene Pvt. Ltd., building agentic automation workflows, after previously working as a Data Analyst Intern at Think AI Corporation.

Degree

B.Tech CSE

AI & ML

CGPA

8.0 / 10

2023 โ€“ 2027

Internships

2

AI & Data

Focus

Agentic AI

RAG ยท LLMs

02.

Skills

Programming

PythonJavaScriptSQL

Python Concepts

OOPFunctionsModules & PackagesFile HandlingException HandlingDecoratorsGeneratorsContext ManagersType Hinting

AI/ML & Generative AI

LangChainLangGraphRAGDocument EmbeddingsVector SearchPrompt EngineeringGenerative AIGroq API

Backend Engineering

FastAPIREST APIsAPI DesignPydantic

Cloud & DevOps

GitDockerDocker ComposeKubernetesAWS (ECR)AWS (ECS)

Data & BI

PandasNumPyMatplotlibPower BITableau
03.

Experience

AI Engineer Intern

Santerra Hygiene Pvt. Ltd.

Jul 2026 โ€“ Sep 2026
  • Build AI-powered automation workflows and practical AI applications using Python, prompt engineering, and model integration to streamline a startup's business operations.
  • Support business data and finance-related processes, applying automation to improve efficiency and scalability of daily operational workflows.

Data Analyst Intern

Think AI Corporation

Apr 2026 โ€“ Jul 2026
  • Migrated legacy reports to Power BI and Tableau, building interactive dashboards to visualize key business metrics and support decision-making.
  • Performed data analysis/EDA using Python and SQL, and designed data pipelines to clean and transform multi-source data into BI-ready formats while gathering requirements with cross-functional teams.
04.

Selected Work

01

Multi-Agent Resume Optimizer

A LangGraph-orchestrated multi-agent pipeline that validates, extracts, and scores resumes against job descriptions (PDF/DOCX/text) using specialized agents with tool calling and Pydantic-structured LLM outputs โ€” backed by a hybrid scoring engine combining deterministic ATS checks with grounded LLM judgment.

LangGraphTool CallingPydanticAgentic AI
View Project โ†’
Multi-Agent Resume Optimizer
02

AI E-Commerce Listing Optimizer

Built a knowledge-base-grounded AI listing optimizer for e-commerce using RAG and multi-agent workflows โ€” combining knowledge retrieval, attribute-aware content generation, keyword optimization, and critic-based quality scoring with deterministic fact-validation and a human review workflow.

Agentic AIRAGLLMAutomation
View Project โ†’
AI E-Commerce Listing Optimizer
03

AI Research Assistant

Engineered a Retrieval-Augmented Generation (RAG) application using FastAPI and LangChain for intelligent document querying โ€” implementing ingestion, chunking, embeddings generation, vector retrieval, and response synthesis pipelines.

FastAPILangChainRAGVector Search
View Project โ†’
AI Research Assistant
05.

Let's work
together

I'm actively looking for opportunities to grow as an AI engineer. If you have a role or project in mind, let's connect!

prekshabarjatya2105@gmail.com โ†’

(+91) 9993098023

New Palasiya, Indore, India, 452001

06.

Resume &
Certifications

Download my resume to learn more about my education, skills, and experience.

โฌ‡ Download Resume

Training & Certifications

๐ŸŽ–

Generative AI, RAG, Multimodal & Agentic AI

CSE (AI & ML) Dept., Acropolis Institute of Technology and Research, with Navigate Labs

Ongoing

Live Tour Guide

A LangGraph agent (running on Groq) reads your intent and drives this page for you โ€” watch the graph light up as it decides.