Available for Internships 2026

Hey, I'm Chaturya Ganne

Building intelligent systems with Deep Learning, Computer Vision, and Generative AI. Currently pursuing MS in Applied ML at University of Maryland.

About Me

I'm a highly motivated Machine Learning Engineer graduating in 2027, with hands-on experience in building and deploying ML models. I specialize in deep learning, computer vision, and Generative AI applications.

Proficient in Python, PyTorch, and TensorFlow, I have a proven track record of translating complex business problems into elegant technical solutions and optimizing models for real-time applications.

My work has been published at prestigious conferences including IWSHM 2025 at Stanford University, and I'm passionate about pushing the boundaries of what's possible with AI.

4+
Publications
6+
ML Projects

Education

University of Maryland, College Park

Masters in Applied Machine Learning
Aug 2025 – Present
Coursework:
Optimisation of Machine Learning Algorithms, Principles of Machine Learning,Computing Systems for Machine Learning

Mahindra University, Hyderabad

Bachelor of Technology, Computer Science Engineering
Aug 2021 – Jun 2025
Coursework:
Data Structures and Algorithms, Deep Learning, Computer Vision

Experience

Data Science Intern

AwoneDataSciences
Jun 2024 – Aug 2024 | Hyderabad, India
  • Applied advanced analytical methods by developing and fine-tuning transformer, diffuser, and vision models to enhance image processing capabilities
  • Designed a virtual call assistant prototype that integrated speech-to-text and text-to-speech functionalities for improved real-time inference
  • Optimized Groq model implementations to accelerate model inference speeds in real-time environments
  • Implemented document question answering solutions to streamline information retrieval tasks and enhance data-driven decision-making

Projects

Featured

AI Medical Diagnosis Tool

Full-stack medical assistant for chest X-ray analysis combining Computer Vision with Generative AI. Uses ResNet50 CNN to detect 15 thoracic diseases with Grad-CAM for interpretability.

Deep Learning Grad-CAM LLaMA 3.2 PyTorch
Published Research

Smart Railway Safety System

Computer Vision sensor system for obstacle detection and track health monitoring using RT-DETR, YOLOv8, and MaskRCNN models. Accepted at IWSHM 2025, Stanford University.

Computer Vision YOLOv8 RT-DETR MaskRCNN

Intelligent Language Learning Agent

AI agent with adaptive difficulty adjustment achieving 94.9% engagement prediction accuracy and 52.5% difficulty optimization using RandomForest models.

ML Scikit-learn Predictive Analytics

Virtual Call Assistant

Consumer digital product integrating speech-to-text and text-to-speech functionalities with NLP capabilities for seamless voice interactions.

NLP Speech Recognition Real-time Processing

Hyperparameter Optimization Research

Research on techniques to obtain optimal hyperparameter combinations for improved ML model performance. Paper accepted at ICOAI 2024.

Research SVM Decision Trees

Breast Cancer Classification

Machine learning model classifying breast cancer tumors using SVM, Random Forest, and Neural Networks with advanced feature engineering.

Classification SVM Neural Networks

Skills

Data Science & Analytics

Python Pandas NumPy Scikit-learn SQL FastAPI Matplotlib Seaborn

Machine Learning & Deep Learning

PyTorch TensorFlow Keras Computer Vision Deep Learning Supervised Learning Unsupervised Learning

Big Data & Cloud

Apache Spark Scala AWS

Technical Tools

Git Docker

Soft Skills

Communication Collaboration Public Speaking Data Visualization

Publications & Achievements

Smart Railway Safety: Integrating Deep Learning with Vision Transformers for Obstacle Detection and Track Health Monitoring

IWSHM 2025, Stanford University

Advanced computer vision techniques for real-time railway safety monitoring using state-of-the-art deep learning models.

Advanced Computer Vision Techniques for Real-Time Railway Safety Monitoring

IWSHM 2025, Stanford University

Research on integrating multiple CV models for comprehensive railway infrastructure monitoring.

Time-Frequency Analysis of Strong Ground Motions from the 1989 Loma Prieta Earthquake

Published Research

Using Seismosignal software to convert FFTs to Continuous Wavelet transform for analyzing seismic risks.

Time-Frequency Analysis of Strong Ground Motions from the 1994 Northridge Earthquake

Published Research

Research analyzing earthquake risks to buildings for better structural planning.

Awards & Recognition

Get In Touch

I'm actively seeking internship opportunities for 2026. Let's discuss how I can contribute to your team!