Laxman Madasu

A Data Scientist with a BS in Data Science, specializing in Python, ML libraries (NumPy, Pandas, NLTK), and MySQL. They build intelligent, AI-powered ...

About

A Data Scientist with a BS in Data Science, specializing in Python, ML libraries (NumPy, Pandas, NLTK), and MySQL. They build intelligent, AI-powered applications, demonstrated by projects like an MCQ Generator (Streamlit, Gemini) and a Code Reviewer (Python, Streamlit, OpenAI API). Their expertise lies in transforming data into practical, innovative solutions, leveraging cutting-edge LLMs to solve real-world problems efficiently.

Skills

Programming Languages

Python

Data Science & ML Libraries

NumPy Pandas Matplotlib Seaborn NLTK Scikit-learn (Sklearn) OpenCV TensorFlow

Databases

MySQL

Machine Learning Concepts

Supervised Learning Unsupervised Learning Feature Engineering Data Preprocessing Hyperparameter Tuning Model Deployment Artificial Neural Networks (ANNs) Convolutional Neural Networks (CNNs) Recurrent Neural Networks (RNNs) Data Augmentation Regularization Techniques Bag-of-Words (BoW) TF-IDF Transfer Learning

Generative AI & NLP

Large Language Models (LLMs) Transformers Attention Mechanism Hugging Face LangChain OpenAI Google GenAI Gemini Model

Web Frameworks/Tools

Streamlit

Statistical Analysis

Descriptive Statistics Inferential Statistics Probability Hypothesis Testing

Database Management

Joins Stored Procedures Triggers Views Indexes

Languages

Python

Generative AI & LLM

LLMs RAG LangChain AI Agents Multi-Agent Workflows Prompt Engineering Function Calling / Tool Calling Structured JSON Generation OpenAI Google Gemini Anthropic Claude Groq DeepSeek Ollama

Backend Frameworks & APIs

FastAPI REST APIs

Databases & Retrieval

MySQL MongoDB ChromaDB Vector Search BM25 Hybrid Retrieval

Document Processing

OCR PaddleOCR Tesseract PyMuPDF pdfplumber

Application & Cloud

Streamlit AWS (EC2, S3, Lambda, SQS) Docker Docker Compose Git GitHub

Programming & Data Science

Python NumPy Pandas Matplotlib Seaborn NLTK Scikit-learn OpenCV

Generative AI

LLMs RAG (dense + BM25 hybrid retrieval) LangChain AI Agents Multi-Agent Pipelines Prompt Engineering Function/Tool Calling Structured JSON Generation OpenAI Gemini Anthropic Groq DeepSeek Ollama

Backend & APIs

FastAPI REST API Design Async/Await SSE Streaming

Document Intelligence

OCR PaddleOCR Tesseract PyMuPDF pdfplumber

Cloud & Application

Streamlit AWS (EC2, S3, Lambda, SQS) Docker Docker Compose Git GitHub

Projects

MCQ Generator Web Application

Streamlit Gemini model

Developed an MCQ Generator Web Application leveraging Streamlit for an intuitive UI and the Gemini model for instant, high-quality question generation. This tool empowers users to transform any text into customizable multiple-choice questions (5, 10, 15, or 20), streamlining content assessment and learning material creation. It provides an efficient solution for educators and trainers to rapidly produce engaging MCQs.

Code Reviewer and Bug Fixing Tool

Python Streamlit OpenAI API

Developed a Python application using Streamlit and OpenAI API to review code and provide feedback on bugs and fixes. Created a simple interface where users can submit their code and get instant feedback. Implemented an efficient system to analyze code, detect bugs, and suggest accurate fixes using the OpenAI API. Made the tool easy to use, helping developers improve their code quickly.

Dog Breed Prediction

Convolutional Neural Network (CNN) Streamlit Data Augmentation Transfer Learning

Engineered a Convolutional Neural Network (CNN) model to accurately predict dog breeds from images using a comprehensive dataset. Created an interactive Streamlit application that allows users to upload dog images and receive real-time breed predictions. Implemented functionality to visualize and display extracted features from the CNN at every convolutional layer, enhancing model interpretability. Optimized model performance through techniques such as data augmentation and transfer learning.

Sentiment Analysis of Hotel Reviews

Machine Learning BoW TF-IDF Naive Bayes Logistic Regression XGboost Streamlit GitHub

Evaluated hotel reviews for sentiment classification using machine learning techniques. Preprocessed text data and extracted features with BoW, and TF-IDF. Trained and evaluated models: Naive Bayes, Logistic Regression, and XGboost. Developed and deployed a real-time sentiment analysis app with streamlit. Achieved 83% accuracy in sentiment classification and documented the project on GitHub.

AI Smart Scanner — Finance Application

Python FastAPI Streamlit MongoDB OCR LLMs LangChain Docker PaddleOCR Tesseract PyMuPDF pdfplumber

Built an AI-powered smart scanner for a finance application that extracts structured information from receipts and financial documents and stores processed data in MongoDB. Developed a Streamlit Smart Scanner that allows users to scan/upload receipts, automatically extract relevant fields, and populate the extracted information into a structured form for user review and correction. Implemented an OCR-based document processing pipeline using PaddleOCR, Tesseract, PyMuPDF, and pdfplumber to extract text and map document content to predefined fields. Integrated LLMs with document processing workflows to handle complex financial documents and convert unstructured document data into structured JSON suitable for downstream processing. Designed the workflow to persist validated extracted information into MongoDB, enabling users to review, update, and manage processed financial records. Developed transaction classification capabilities combining rule-based logic and fuzzy matching to categorize financial transactions and improve classification using user feedback.

Maya - AI Website Generation Platform

Python FastAPI LLMs RAG Streamlit JSON MongoDB ChromaDB Gemini Groq OpenAI Anthropic Cohere DeepSeek Ollama

Engineered a FastAPI + MongoDB LLM platform converting natural-language prompts into schema-valid UI page trees for websites, portfolios, and reusable components. Architected a multi-stage RAG generation pipeline (planner → grounded generator → validator → self-repair → quality scorer) that lifted structure validity from 33% to 100% and component correctness from 98.8% to 100% across a 12-page evaluation set. Implemented hybrid RAG retrieval (dense embeddings + BM25, fused via Reciprocal Rank Fusion) over a 154-component knowledge base, eliminating hallucinated component types from generated output. Built a provider-agnostic LLM layer spanning 7 providers (Gemini, Groq, OpenAI, Anthropic, Cohere, DeepSeek, Ollama) with cross-provider fallback and per-stage token/cost accounting. Delivered SSE streaming generation and session version history (undo/revert), validated by a 300-prompt benchmark corpus and 265 unit tests.

GeethAI - AI Application & Agent Platform

FastAPI Python MongoDB Streamlit LLMs AI Agents Tool Calling Multi-Tenant Architecture OpenAI Anthropic Gemini Groq Cohere DeepSeek Ollama

Developed a multi-tenant LLM application platform enabling non-engineers to build and publish AI applications across three execution modes: conversational chat, tool-calling agents, and deterministic flows. Designed a provider-agnostic LLM abstraction across 7 providers (OpenAI, Anthropic, Gemini, Groq, Cohere, DeepSeek, Ollama), letting each application swap models purely through configuration. Established production reliability primitives from scratch — circuit breakers, MongoDB-backed distributed locking, idempotency gating, dead-letter queues, and retry/timeout policies — validated by a 190-test suite. Enforced strict multi-tenant data isolation via a database-proxy layer injecting tenant context into every query, combined with deny-by-default tool scoping to block cross-tenant access. Diagnosed and resolved a critical multi-turn agent reliability issue (tool-call success stuck at 57%) by fixing cross-turn context persistence, restoring reliable multi-step tool execution.

Experience

AI & ML Engineer

Geeth LLC

- Present

Worked on Maya, an AI-powered website generation platform that enables users to create websites, portfolios, sections, buttons, and other UI components using natural-language prompts. Developed the RAG + LLM generation workflow that understands a library of custom UI components built by frontend developers and generates websites based on their JSON component definitions. Implemented retrieval-based prompting so LLMs could identify and reuse the appropriate Angular-based components and their JSON schemas, enabling consistent and structured UI generation instead of generating arbitrary components. Contributed to the Streamlit-based frontend, allowing users to interact with the AI generation workflow and view recent sessions, live website previews, generated JSON, and generated code. Developed structured JSON-based page generation workflows using LLMs and RAG, improving component selection and reducing unsupported or hallucinated UI components. Worked on a multi-tenant AI application platform that enables users to build, configure, deploy, and integrate AI-powered applications such as AI agents, conversational chatbots, and workflow-based applications. Developed AI application workflows supporting conversational chat, tool-calling agents, and deterministic flows, enabling applications to perform actions and interact with external systems rather than only generate text. Built use cases including e-commerce AI assistants for product discovery and ordering, website chatbots for customer interaction, and automated offer-letter generation. Enabled businesses to build domain-specific AI applications such as loan and mortgage workflows that collect customer information, process application data, and support human-in-the-loop review and approval processes. Designed the platform to allow AI applications to be embedded and integrated into existing business applications, enabling organizations to add AI capabilities without building individual AI systems from scratch. Implemented a provider-agnostic LLM architecture supporting multiple LLM providers, allowing applications to switch models without changing application-level logic. Implemented production reliability and multi-tenant isolation using circuit breakers, distributed locking, idempotency, retry/timeout handling, dead-letter queues, and database-level tenant isolation.

Education

Master of Computer Applications (MCA)

Jawaharlal Nehru Technological University Hyderabad (JNTUH)

-

Bachelor of Science (Data Science)

Satavahana University, Karimnagar

-

Certifications

Certificate of Course Completion in Data Science

Innomatics Research Labs

Machine Learning with Python

IBM Developer skills Network

Exploratory Data Analysis Module Completion Certificate

Innomatics Research Labs

Contact

Email: madasulaxman028@gmail.com