Document

SUMMARY

B.Tech Information Technology student (Expected 2026) with internship and project experience in AI and Data Science, strong in Python, Machine Learning, NLP, and Deep Learning. Currently learning Generative AI, LLMs, Prompt Engineering, and Agentic AI using LangChain, LangGraph, and RAG. Seeking entry-level Data Analyst, AI, or Software roles to apply technical skills in real-world solutions.

EDUCATION

B.Tech in Information Technology

Expected 2026

S.V. College of Engineering, Tirupati

89%

Intermediate (MPC)

2020–2022

Narayana Junior College, Nellore

95%

Programming Languages

C, Python, Java, SQL

Databases

MySQL

Technical Skills

Machine Learning, Deep Learning, NLP, Data Structures & Algorithms

Libraries

NumPy, Pandas, Scikit-learn, NLTK, Keras, TensorFlow

Web Frameworks

Flask, FastAPI

Cloud Skills

AWS (EC2, S3, IAM, Lambda, CloudWatch)

Tools

Git, GitHub, Jupyter Notebook, Visual Studio Code

Soft Skills

Analytical Thinking, Communication, Team Collaboration, Eagerness to Learn

AI Developer Intern

May 2025 – Jun 2025

SmartBridge

Remote

Developed 3 AI-based chatbot modules using Python and IBM Granite to handle healthcare-related queries, structuring prompt workflows to generate relevant and meaningful responses.
Built and integrated a Streamlit frontend interface to enable real-time user interaction, input handling, and dynamic response display.
Connected the application with a MySQL backend to implement secure user authentication and structured storage of user interaction data.
Organized the application into modular components to ensure smooth communication between AI models, frontend UI, and backend database systems.

Data Science Intern

Jan 2025 – Apr 2025

UptoSkills

Remote

Built automated web-scraping pipelines using Python, Playwright, and BeautifulSoup to collect and preprocess large-scale datasets from dynamic web applications.
Engineered data extraction workflows capable of handling JavaScript-rendered content, reducing manual data collection effort by 70%.
Performed data cleaning, validation, and structuring to transform raw scraped data into analysis-ready datasets.
Standardized scraping processes and optimized data handling pipelines to improve dataset reliability and processing efficiency.

Email Spam or Ham Classification

Built a complete end-to-end NLP pipeline to preprocess 5,000+ SMS messages using tokenization, stopword removal, stemming, and text normalization techniques.
Applied TF-IDF vectorization to transform unstructured text data into high-dimensional numerical feature representations for model training.
Implemented and compared Bernoulli and Multinomial Naive Bayes models, achieving 98.5% accuracy and 100% precision based on confusion matrix evaluation.
Deployed the trained model using Flask to build a web-based application enabling real-time spam classification and user input handling.

Potato Leaf Disease Classification

Designed and trained a custom Convolutional Neural Network (CNN) using TensorFlow/Keras to classify 1,200+ labeled leaf images across 3 disease categories.
Performed image preprocessing and augmentation (resizing, normalization, rotation, flipping) to enhance dataset diversity and improve model generalization.
Applied regularization techniques such as dropout and early stopping to reduce overfitting and stabilize validation performance.
Achieved 99% training accuracy and 96% validation accuracy through systematic hyperparameter tuning and performance optimization.