Sunil Surineni
About Sunil Surineni
Sunil Surineni is a Research Software Engineer II at Blaize, where he has worked since 2014 in Hyderabad, India. He specializes in autonomous driving simulations, machine learning frameworks, and sensor fusion processes, contributing to various innovative projects in the field.
Work at Blaize
Sunil Surineni has been employed at Blaize as a Research Software Engineer II since 2014. He has spent a decade in this role, contributing to various projects in the Hyderabad Area, India. His work includes designing and implementing a Unity-based simulator for autonomous driving, which interfaces with Matlab for the autonomous software stack and algorithms. Additionally, he has led the architecture, design, and development of a machine learning framework agnostic deployment tool for Thinci IP, supporting multiple frameworks such as Pytorch, Tensorflow, Caffe2, Caffe, and ONNX.
Education and Expertise
Sunil Surineni studied at Kakatiya University from 2009 to 2013, earning a degree that laid the foundation for his career in software engineering. He furthered his education at Vellore Institute of Technology, where he specialized in automotive electronics and obtained a Master of Technology (MTech) from 2013 to 2015. His academic background supports his expertise in developing advanced technologies in the field of autonomous systems and machine learning.
Background
Sunil Surineni has a strong background in research and development, particularly in the areas of autonomous driving and machine learning. His experience includes contributions to high-definition mapping algorithms with spline optimizations aimed at reducing HD map storage requirements. He has also developed a novel sensor-fusion process that integrates Lidar point cloud, RGB Camera, and HD map data, with a pending patent for this innovation.
Achievements
Throughout his career, Sunil has been involved in significant projects, including the design and development of Generative Adversarial Networks (GAN) for synthetic data generation as part of the AI Studio project. His work in creating a machine learning framework agnostic deployment tool demonstrates his ability to support various AI frameworks, enhancing the versatility of machine learning applications.