Nimrod Gileadi
Member Of Technical Staff at Genesis AI
London, England, United Kingdom
Summary
🤩
Rockstar🎓
Top SchoolNimrod Gileadi is a robotics-focused software engineer with 13 years of experience building high-performance simulation, control and data pipelines, currently a Member of Technical Staff at Genesis AI after a senior research-engineering tenure at DeepMind. He is a core contributor to the open-source MuJoCo physics stack and related DeepMind tooling, combining low-level C/C++ bindings work with Python orchestration and DevOps to push sim-to-real robotics research. His expertise spans model-predictive control, RL/imitation learning, large-scale simulated data generation and system identification, with a track record of performance optimization from physics engines to on-robot deployment. Nimrod’s contributions show a pragmatic emphasis on robustness—thread safety, memory management and tooling for unattended large-scale collection—enabling reliable transfer of complex dexterous policies to real robots. A Cambridge-trained engineer who also spent time at MIT, he brings both deep systems craftsmanship and research-driven experimentation to applied robotics problems.
13 years of coding experience
14 years of employment as a software developer
Electronic Engineering and Computer Science, Electronic Engineering and Computer Science at Massachusetts Institute of TechnologyBA MEng (Hons) Information and Computer Engineering, BA MEng (Hons) Information and Computer Engineering at University of Cambridge
Hebrew, English, Spanish
Stackoverflow
535reputation
31kreached
9answers
2questions
Github Skills (40)
simulation10
c-language10
python10
simulator10
simulations10
memory-management10
reinforcement-learning10
deeplearning-ai10
deep-learning10
physics10
mujoco10
cprogramming-language10
apidoc9
multithreading9
machine-learning9
Programming languages (10)
Github contributions (5)
google-deepmind/mujoco_mpc
Dec 2022 - Mar 2023
Real-time behaviour synthesis with MuJoCo, using Predictive Control
Role in this project:
Back-end Developer
Back-end DeveloperContributions:1 release, 99 reviews, 46 commits in 3 months
Contributions summary:Nimrod primarily contributed to the core logic and functionality of the MuJoCo MPC project. Their commits focused on modifying and improving the iLQGPlanner, including debugging utilities, thread safety, and performance improvements. They also made adjustments to the Agent class and Trajectory class, suggesting a focus on the core control and planning elements of the project. These changes were likely aimed at improving the performance and stability of the model predictive control algorithms.
roboticsmpcpybulletsynthesismodel-predictive-control
google-deepmind/mujoco
Mar 2022 - Jan 2023
Multi-Joint dynamics with Contact. A general purpose physics simulator.
Role in this project:Back-end Developer
Back-end DeveloperContributions:2 releases, 36 reviews, 42 commits in 10 months
Contributions summary:Nimrod's contributions primarily focused on enhancing the MuJoCo physics simulator, as demonstrated by the addition of a `free()` method for memory management within the Python bindings. Further, the user updated the MuJoCo library version, refactoring code, and providing fixes and improvements. The contributions highlight a strong emphasis on improving the MuJoCo library's functionality, with a focus on Python bindings.
physics-enginephysicsroboticsrobotics-simulationbullet-physics
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.