Welcome to my portfolio

Jhanavi Putcha

Machine Learning Engineer | Data Scientist

Building AI-driven solutions that transform data into measurable business impact—from computer vision systems processing 30M+ daily inspections to production-grade ML models.

About Me

I'm a Machine Learning Engineer with a Master's degree in AI from the University at Buffalo, focused on building intelligent systems that solve real-world problems at scale. My expertise spans computer vision, deep learning, and end-to-end ML pipeline development—from data preprocessing to production deployment.

I've worked on AI solutions ranging from industrial inspection systems processing millions of daily items to market segmentation models driving business strategy. I thrive at the intersection of research and application, leveraging tools like TensorFlow, PyTorch, and AWS to deliver measurable outcomes.

Deep Learning

Building neural networks for computer vision, NLP, and predictive analytics

Data Engineering

Processing and analyzing large-scale datasets for actionable insights

ML Deployment

Deploying production-ready models with AWS and cloud infrastructure

Technical Skills

Languages

PythonJavaScriptCSQLRJavaHTML

Frameworks & Libraries

Scikit-LearnTensorFlowPyTorchPandasNumPyNLTKSpaCyFlaskSpark

Tools

GitHubMySQLPower BITableau

Cloud (AWS)

EC2S3SageMakerCognitoAPI GatewayDynamoDB

Experience

Project Eagle Eyes – Vision AI for Industrial Printing

Nissha Medical Technologies

Capstone Project
Aug 2025 – Dec 2025Buffalo, NY
  • Architected an AI-driven inspection system to detect and analyze Q-Block defects in ultra-high-speed ticket printing lines processing AI-driven 30M+ tickets daily
  • Trained a YOLOv8-based object detection model achieving high accuracy in localizing large and small Q-Blocks from production images
  • Developed color fading and area-based quality analytics by extracting pixel-level features (HEX/RGB, dimensions) from detected regions
  • Built visualization pipelines to track color degradation trends, enabling early detection of machine wear and reducing downtime
  • Implemented automated GOOD/NOT GOOD classification system, significantly reducing manual inspection dependency and improving defect detection consistency automated GOOD/NOT GOOD classification
YOLOv8Computer VisionOpenCVPythonData Analytics

Artificial Intelligence Intern

AVR Research and Development Pvt. Ltd.

Internship
Feb 2024 – Jun 2024India
  • Executed comprehensive data pre-processing and cleaning procedures, enhancing dataset quality and reducing model training time by 25%
  • Designed and implemented ML models using diverse algorithms (decision trees, random forests, SVMs, neural networks), achieving 15% improvement in predictive accuracy
  • Conducted in-depth model evaluation and hyperparameter tuning, optimizing performance across multiple deployments
  • Successfully deployed models into production, contributing to data-driven decision-making and measurable business impact production-grade ML
Machine LearningPythonScikit-LearnData PreprocessingModel Deployment

Machine Learning Intern

Feynn Labs

Internship
Mar 2023 – May 2023Remote
  • Developed ML algorithms for market segmentation , enabling targeted marketing strategies and improving customer engagement through high-value segment identification
  • Collaborated with cross-functional teams to gather, clean, and preprocess large-scale datasets, ensuring data integrity for model training
  • Leveraged data analysis techniques to uncover actionable business insights, directly influencing product positioning and customer acquisition strategies actionable business insights
Market SegmentationPythonData AnalysisClusteringBusiness Intelligence

Featured Projects

A selection of projects showcasing my work in ML, computer vision, and AI applications

Music Generator using Genetic Algorithm

Problem

Most music generators depend on large datasets, making it hard to personalize output without retraining.

Solution

Built a melody generator that evolves music using a genetic algorithm and improves based on iterative selection (fitness).

Outcome

Generates evolving melodies with controllable variation and selection-driven improvement.

TypeScriptGenetic AlgorithmsUI/Frontend
View on GitHub

Comparative Analysis of RL Algorithms (Discrete & Continuous)

Problem

Choosing the right RL algorithm depends heavily on the action space and environment dynamics.

Solution

Implemented and compared PPO, DQN, DDQN, and A2C across discrete and continuous action-space settings.

Outcome

Analysis highlights trade-offs in stability, sample efficiency, and performance by action space.

PythonReinforcement LearningJupyter Notebook
View on GitHub

Crop Prediction using ThingSpeak

Problem

Farmers need data-driven crop recommendations based on real-time environmental conditions.

Solution

Built a crop prediction workflow using ThingSpeak sensor data (temperature, pH, rainfall, humidity) to guide crop selection.

Outcome

Improved crop selection decisions using real-time sensor-driven insights.

PythonThingSpeakData AnalysisJupyter Notebook
View on GitHub

Surya Namaskar Trainer

Problem

Beginners struggle to learn proper Surya Namaskara (Sun Salutation) yoga poses without real-time guidance, leading to incorrect postures and potential injury.

Solution

Built an interactive platform that uses computer vision to provide real-time feedback on yoga pose correctness and alignment.

Outcome

Published research paper (DOI: JETIR2404467) demonstrating effective pose correction for yoga practitioners

PythonOpenCVMediaPipe
View on GitHub

Warehouse Robot using Q-Learning and SARSA

Problem

Warehouse logistics require efficient automated systems for picking up and delivering parcels between locations.

Solution

Developed a reinforcement learning agent using Q-Learning and SARSA algorithms to autonomously navigate warehouse environments.

Outcome

Agent successfully learns optimal paths for parcel delivery in complex warehouse grid environments

PythonGymnasiumReinforcement Learning
View on GitHub

AI Recipe Generator

Problem

Users often have ingredients but lack inspiration or knowledge to create recipes, especially from visual input.

Solution

Created an AI-powered application that generates food recipes from both image and text inputs, featuring an interactive chatbot powered by OpenAI.

Outcome

Delivers personalized recipe recommendations based on available ingredients through natural conversation

PythonFlaskOpenAI API
View on GitHub

Achievements & Recognition

ML Speaker

Delivered an engaging machine learning-focused talk to an audience of 200+ students , sharing insights on AI/ML concepts and career paths. Received a Letter of Appreciation for knowledge sharing and presentation excellence.

ML Competition Winner

Secured 3rd place in a competitive ML challenge by developing a production-grade AI solution, demonstrating strong problem-solving skills and ability to deliver practical, deployable models under pressure.

Institutional Interface Developer

Built a comprehensive platform that streamlined assignment submissions and improved academic workflows for the institution, showcasing full-stack development capabilities and user-centric design thinking.

Get In Touch

I'm always open to discussing new opportunities, AI/ML projects, or just connecting with fellow tech enthusiasts.