Summary
Madhumitha Sakthi is a Senior ADAS R&D Engineer at Qualcomm with nine years of experience developing deep learning perception systems for autonomous driving, specializing in multi-object multi-class tracking and multi-camera depth estimation. She holds a Ph.D. in Electrical and Computer Engineering from UT Austin, where her research produced adaptive radar acquisition algorithms and extreme model compression techniques that achieved large sample reductions and up to 35x compression with minimal accuracy loss. At Qualcomm she has translated academic advances into production-focused innovations—filed multiple patents and led work on transformer-based trackers, occlusion detection, and neural rendering for static scene reconstruction. Her background spans radar-aware object detection (DETR-Radar), video and compression analysis presented at CVPR workshops, and efficient ML for resource-constrained platforms, reflecting a rare blend of signal-processing rigor and practical deep learning engineering.
8 years of coding experience
4 years of employment as a software developer
Doctor of Philosophy - PhD, Electrical and Computer Engineering, Doctor of Philosophy - PhD, Electrical and Computer Engineering at The University of Texas at Austin
Bachelor's degree, Electrical, Electronics and Communications Engineering, Bachelor's degree, Electrical, Electronics and Communications Engineering at SASTRA UNIVERSITY
High school, Computer Science, High school, Computer Science at Bala vidya mandir senior secondary school, Adyar
German, English