Jyotsna Verma
Senior Consultant at Daimler Truck Innovation Center India (DTICI)
Bengaluru, Karnataka, India
Summary
🤩
Rockstar🎓
Top SchoolJyotsna Verma is a Senior Consultant based in Bengaluru with four years of professional experience combining system engineering, technical leadership, and backend performance work. She has progressed through roles at Cognizant and TCS into her current position at Daimler Truck Innovation Center India, demonstrating strong operational and delivery chops in enterprise environments. On GitHub she contributes to the high-profile apache/tvm project, focusing on Hexagon backend performance, quantization ops, and on-device profiling—showing a knack for low-level optimization in ML compiler stacks. Her background in system administration and customer-facing roles gives her a practical perspective on reliability and observability in production systems. Colleagues know her for translating complex hardware-software interactions into measurable performance improvements. She holds a BE in Computer Science from M S Engineering College, Bangalore.
4 years of coding experience
8 years of employment as a software developer
BE - Bachelor of Engineering, Computer Science, BE - Bachelor of Engineering, Computer Science at M S Engineering College, BANGALORE
Github Skills (17)
performance-monitor10
hexagons10
compiler-compiler10
performance-analysis10
compiler10
c-language9
python9
cprogramming-language9
deep-learning8
deeplearning-ai8
machine-learning8
tensor7
gpu7
opencl5
vulkan5
Programming languages (2)
Github contributions (5)
apache/tvm
Apr 2022 - Oct 2022
Open deep learning compiler stack for cpu, gpu and specialized accelerators
Role in this project:
Back-end Developer & Performance Engineer
Back-end Developer & Performance EngineerContributions:55 reviews, 5 commits, 5 PRs in 6 months
Contributions summary:Jyotsna primarily focused on improving the performance and functionality of the Hexagon launcher within the TVM compiler stack. Contributions included enabling custom logging for the Hexagon launcher, addressing formatting errors, and implementing the avg_pool2d slice operator, and implementing quantization related operations within the Hexagon module. Further, the user integrated instrumentation based profiling and updated search patterns for on-device runs, demonstrating a strong focus on system optimization. These commits indicate an effort to enhance the compiler's efficiency and debugging capabilities for Hexagon-based hardware.
metalvulkancompilertensoropencl
jverma-quic/tvm
Apr 2022 - Oct 2023
Open deep learning compiler stack for cpu, gpu and specialized accelerators
Contributions:74 pushes, 10 branches in 1 year 6 months
cpugpu-programminggpu-accelerationtvmdeep-learning
Find and Hire Top DevelopersWe’ve analyzed the programming source code of over 60 million software developers on GitHub and scored them by 50,000 skills. Sign-up on Prog,AI to search for software developers.