Manohar Manohar
Senior Software Engineer at NVIDIA
Bengaluru, Karnataka, India
Summary
👤
Senior🎓
Top SchoolManohar is a Senior Software Engineer with 10 years of experience specializing in 3D reconstruction, SLAM, and state estimation for robotics and computer vision applications. Based in Bengaluru, he has driven performance-critical vision pipelines at Qualcomm—achieving up to 250x GPU speedups—and built HD map validation and KPI tooling at NVIDIA using modern C++ for autonomous systems. His open-source contributions include core control-system work in the widely used Control Toolbox and maintenance improvements to Theano, reflecting a balance of algorithmic depth and pragmatic code hygiene. He also built an end-to-end visual-inertial odometry stack running on embedded hardware (Jetson Nano + Pixhawk), showing a hands-on ability to move research into deployable systems.
10 years of coding experience
5 years of employment as a software developer
Mathematics, Mathematics at Sri Chaitanya College of EducationMaster of Science - MS Mathematics and Computer Science, Master of Science - MS Mathematics and Computer Science at Indian Institute of Technology, Kharagpur
Sanskrit, Hindi, Telugu, Kannada, English
Github Skills (14)
control-theory10
controls10
c-language10
eigen10
cprogramming-language10
python10
linear-algebra10
control-flow10
theano10
numpy10
cpp8
machine-learning8
automatic-differentiation8
scipy6
Programming languages (7)
Github contributions (5)
Theano/Theano
Nov 2016 - Nov 2016
Theano was a Python library that allows you to define, optimize, and evaluate mathematical expressions involving multi-dimensional arrays efficiently. It is being continued as PyTensor: www.github.com/pymc-devs/pytensor
Role in this project:
Back-end Developer
Back-end DeveloperContributions:10 commits, 4 PRs, 6 comments in 4 days
Contributions summary:Manohar primarily contributed to the Theano library by modifying and refactoring the import statements of the `numpy` library within the codebase. They updated various benchmark files and core library files, ensuring a consistent import style. Their changes touched upon multiple files related to autoencoders, convolution, and regression tasks. These actions suggest a focus on code maintenance and library consistency within the project.
python-librarymathmulti-dimensionalpythonevaluate
ethz-adrl/control-toolbox
Mar 2020 - Mar 2020
The Control Toolbox - An Open-Source C++ Library for Robotics, Optimal and Model Predictive Control
Role in this project:Back-end Developer
Back-end DeveloperContributions:5 commits, 1 PR, 9 comments in 2 days
Contributions summary:Manohar contributed to the core functionality of the Control Toolbox library, focusing on the implementation of linear system components. Their work included adding features for computing controllability and observability Gramians for both continuous-time and discrete-time linear systems, along with the corresponding matrices. The user refactored and improved the DiscreteLinearSystem, introducing the DiscreteLTISystem class. This work directly supports the library's control-systems and trajectory-optimization capabilities.
nonlinear-optimizationautomatic-differentiationmodel-predictive-controloptimal-controlrigid-body-dynamics
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.