Recent B.Tech graduate in Computer Science & Engineering (AI & ML) passionate about building data-driven solutions across Artificial Intelligence, Machine Learning, Data Science, Data Analytics, and Data Engineering.

I enjoy working across the complete data and AI lifecycle — from data collection, cleaning, SQL analysis and feature engineering to machine learning, deep learning, LLM applications, RAG pipelines, and deployment.

💡 Core Focus: AI/ML · Data Science · Data Analytics · Data Engineering · Generative AI

🐍 Primary Language: Python

📊 Data: SQL · Pandas · NumPy · Data Preprocessing · EDA

🤖 AI/ML: Scikit-learn · PyTorch · NLP · Deep Learning · Transformers

🧠 GenAI: LLMs · RAG · Vector Databases · Prompt Engineering

☁️ Cloud & Tools: GCP · BigQuery · Cloud Storage · Git · GitHub · Google Colab

• Machine learning models for real-world problems
• NLP and text classification systems
• Deep learning using PyTorch
• Transformer-based AI applications
• Model evaluation and optimization

• Exploratory Data Analysis (EDA)
• Data cleaning and preprocessing
• Feature engineering
• Statistical analysis
• SQL-based data analysis
• Data visualization and reporting

• Data preprocessing and transformation pipelines
• Structured and unstructured data handling
• SQL and relational databases
• ETL/ELT concepts
• Data pipelines supporting ML and analytics workflows
• Cloud-based data workflows

• Large Language Model applications
• Retrieval-Augmented Generation (RAG)
• Semantic search and vector databases
• Prompt engineering
• Multimodal AI applications

A multi-source Retrieval-Augmented Generation system designed to retrieve information from multiple knowledge sources and generate source-grounded answers.

Tech: Python · RAG · ChromaDB · Sentence Transformers · Groq · LLaMA · Streamlit

Highlights

• Indexed 703 records into ChromaDB
• Implemented semantic retrieval and fallback strategies
• Used embedding-based search for relevant information retrieval
• Generated responses using LLaMA 3.3 70B through Groq
• Added source attribution and hallucination checks
• Implemented entity and relationship linking across sources

An end-to-end OCR + Machine Learning + Document AI pipeline for extracting structured information from receipts.

Tech: Python · PyTorch · Hugging Face · OCR · LayoutLMv3 · CORD · Flask

Pipeline

Document → OCR → Text + Bounding Boxes → LayoutLMv3 → Information Extraction → Structured Data

Highlights

• Fine-tuned LayoutLMv3 for receipt information extraction
• Processed OCR text and spatial bounding-box information
• Trained using the CORD dataset
• Extracted fields such as vendor, date and total amount
• Built an inference pipeline and web application

An AI-based grievance management system combining NLP, machine learning, multimodal processing and databases.

Tech: Python · Flask · Transformers · PyTorch · Scikit-learn · CLIP · MySQL

Highlights

• Classified complaints using NLP and ML techniques
• Processed structured and unstructured data
• Used CLIP embeddings and cosine similarity for multimodal comparison
• Implemented duplicate complaint detection
• Integrated ML workflows with a Flask backend and MySQL

Conversational AI application built using LLaMA models and the Groq API.

Tech: Python · LLaMA · Groq API · Prompt Engineering · Gradio

• Developed an interactive conversational interface
• Applied prompt engineering techniques
• Evaluated and improved model responses
• Built an end-to-end LLM application

NLP-based machine learning system for classifying AI-generated and human-written text.

Tech: Python · Pandas · Scikit-learn · TF-IDF · NLP

• Performed text preprocessing
• Applied TF-IDF feature extraction
• Trained and evaluated classification models
• Built a complete text classification workflow

Python · SQL · JavaScript · HTML · CSS

Pandas · NumPy · Exploratory Data Analysis · Data Cleaning · Data Preprocessing · Feature Engineering · Statistical Analysis · Data Visualization

SQL · MySQL · MongoDB

ETL/ELT · Data Pipelines · Data Transformation · SQL · Structured & Unstructured Data · Cloud Storage · BigQuery

Scikit-learn · Regression · Classification · Clustering · Ensemble Learning · Model Evaluation

PyTorch · ANN · CNN · RNN · Transfer Learning

NLP · Transformers · LLMs · RAG · Prompt Engineering · Semantic Search · Vector Databases

OCR · EasyOCR · LayoutLMv3 · CLIP · Document AI · Information Extraction

Google Cloud Platform · BigQuery · Cloud Storage · Flask · Streamlit · Gradio

Git · GitHub · VS Code · Google Colab · Jupyter Notebook

             DATA
               │
               ▼
      ┌─────────────────┐
      │ Data Collection │
      └────────┬────────┘
               ▼
      ┌─────────────────┐
      │ Cleaning & EDA  │
      └────────┬────────┘
               ▼
      ┌─────────────────┐
      │ Transformation  │
      │ & Feature Eng.  │
      └────────┬────────┘
               ▼
      ┌─────────────────┐
      │ ML / DL / NLP   │
      └────────┬────────┘
               ▼
      ┌─────────────────┐
      │ Evaluation      │
      └────────┬────────┘
               ▼
      ┌─────────────────┐
      │ Deployment      │
      └────────┬────────┘
               ▼
      ┌─────────────────┐
      │ Analytics / AI  │
      │ Application     │
      └─────────────────┘

• Advanced Machine Learning
• Generative AI and LLM applications
• Retrieval-Augmented Generation
• Data Engineering workflows
• Cloud data platforms
• BigQuery and analytical data processing
• Data visualization and business analytics
• Production-oriented AI/ML systems

I'm interested in opportunities across:

AI/ML Engineering · Data Science · Data Analytics · Data Engineering · Generative AI · NLP · Machine Learning

I’m particularly interested in roles where data, machine learning and software engineering come together to solve real-world problems.

💼 LinkedIn: linkedin.com/in/potnuru-rutikasri

📧 Email: rutikasripotnuru20@gmail.com

💻 GitHub: github.com//github.com/Rutikasri

Turn data into insights, insights into models, and models into useful products.