Summary
Madhumitha Sridhara is a software engineer with about nine years of experience building high-performance ML inference and GPU software, currently at Meta after leading MLPerf inference submissions at NVIDIA. She specializes in TensorRT and Triton optimizations, performance analysis for deep learning workloads, and has helped redesign TensorRT for ISO 26262 functional safety in autonomous systems. Her background spans low-level C++ systems, JVM/Scala infrastructure at Goldman Sachs, and GPU architecture analysis from internships at Intel and academic work at Carnegie Mellon. She holds an M.S. in Electrical and Computer Engineering with a focus on computer architecture and an earlier B.Tech where she explored biomedical signal and image processing, including published work on early Alzheimer’s detection from MRI. Colleagues describe her as a pragmatic engineer who bridges research-grade performance tuning with production deployment requirements.
9 years of coding experience
4 years of employment as a software developer
Master’s Degree, Electrical and Computer Engineering, Master’s Degree, Electrical and Computer Engineering at Carnegie Mellon University
Bachelor of Technology (B.Tech.), Electrical, Electronics and Communications Engineering, Bachelor of Technology (B.Tech.), Electrical, Electronics and Communications Engineering at National Institute of Technology Karnataka
Marathi, English, Kannada, Hindi