Harshavardhan Patil

Hey there! I am Harshavardhan Patil, a motivated Machine Learning professional pursuing a Master of Science in Data Science at the University of Maryland, College Park, with an anticipated graduation in December 2025. I bring multiple years of industry experience, a strong academic foundation and a passion for leveraging cutting-edge AI and machine learning techniques to solve real-world problems.

My expertise lies in developing and deploying advanced machine learning and deep learning models across diverse domains such as computer vision, natural language processing, and probabilistic modeling. I have hands-on experience with frameworks like PyTorch, TensorFlow, and Scikit-Learn, which I use to build state-of-the-art solutions, including Vision Transformers (ViTs), Convolutional Neural Networks (CNNs), as well as ensemble-based methods.

I specialize in cloud-based data engineering and machine learning pipelines, utilizing AWS services such as EC2, Lambda, Fargate, and S3 to design scalable, high-performance architectures. My projects include a ViT-powered image-to-GPS prediction system and a sports betting prediction platform, both demonstrating innovative model architectures and robust data processing capabilities. I am adept at optimizing workflows using tools like Docker, Git, Snowflake, and NVIDIA DALI, achieving significant cost and time savings.

In addition to my technical skills, I have a proven track record of leadership and impact in professional roles. As a Data Engineer at Principal Global Services, I spearheaded the development of data products and validation features that resulted in multi-million-dollar savings and automated rectification processes. I thrive in collaborative environments, driving cross-functional project alignment and delivering impactful business outcomes.

Fluent in multiple programming languages, including Python, Java, and SQL, I am deeply committed to harnessing the power of machine learning to drive innovation and create value across industries.