Kalyan Naik Vankudothu

I’m a motivated and detail-oriented Computer Science graduate with a strong foundation in Artificial Intelligence, Data Engineering, and Cloud Computing. I have hands-on experience designing and deploying cloud-based applications on Microsoft Azure, as well as building full-stack web solutions and AI-driven systems. I’m skilled in developing machine learning models, deep learning frameworks, and optimizing large-scale data pipelines, with proficiency in Python, C#, and modern web technologies.

Currently, I’m pursuing my Master’s in Computer Science at Lawrence Technological University, where I’m conducting research on applying deep learning to biometric security and infrastructure monitoring. I’m passionate about using AI and data-driven approaches to tackle real-world challenges.

Previously, as a Junior Developer, I contributed to coding, debugging, and designing software applications, improving system efficiency and performance. I bring strong skills in Python, Java, and C++, along with a solid understanding of data structures and algorithms. Known for my problem-solving ability, collaborative mindset, adaptability to new technologies, and delivering quality work under tight deadlines, I’m now seeking a full-time opportunity where I can apply my skills in AI, data engineering, and cloud development in a forward-thinking environment.

• Coursera: Image Denoising Using Autoencoder in Keras and Python
• Cisco: Programming Essentials in Python
• Microsoft: Career Essentials in Generative AI by Microsoft and LinkedIn
• LinkedIn Learning: Ethics in the Age of Generative AI,
• Azure AI Fundamentals (AI-900) Cert Prep: 1 Conversational AI on Azure,
• Generative AI: The Evolution of Thoughtful Online Search,
• Introduction to Artificial Intelligence,
• Learning Microsoft 365 Copilot and Business Chat,
• Streamlining Your Work with Microsoft Copilot,
• What is Generative AI

Exploring Fingerprint Individuality and Commonalities: Deep Learning Insights, Conducting research at Lawrence Technological University to analyse fingerprint individuality and commonalities using deep learning techniques., Implemented CNNs and pretrained models (VGG16, ResNet50, Efficient Net) for Binary and Multi-Class Classification tasks., Achieved high accuracy in fingerprint recognition using Efficient Net, highlighting the effectiveness of deep learning in biometric security., Discovered unexpected similarities among fingerprints, challenging traditional uniqueness assumptions., Examined the impact of missing fingerprint samples (e.g., left index finger) on model performance., Leveraging TensorFlow, Keras, and feature extraction to enhance AI-driven biometric security systems.

 Doctor Appointment System:Designed a web application using Angular (frontend) and .NET (backend) with a MySQL database hosted on Azure., Enabled seamless patient booking, handling over 100 weekly appointments efficiently., Integrated Azure cloud services for secure and scalable data management., Implemented real-time updates, doctor availability tracking, and automated email notifications., Incorporated role-based access controls to ensure data privacy compliance., Reduced appointment booking time by 50% compared to previous systems.

 Concrete Cracks Detection Using Deep Learning Techniques: Developed a deep learning model to detect concrete cracks and corrosion using image classification techniques., Utilized CNN architectures such as ResNet and Efficient Net to enhance feature extraction and detection accuracy., Trained and tested the model on real-world datasets, achieving high precision in structural damage assessment., Implemented preprocessing techniques like edge detection and thresholding for improved crack identification., Applied AI-driven insights to aid in automated infrastructure maintenance and safety monitoring.