Rohun Kulkarni
Member Of Technical Staff at Foundry Robotics
Palo Alto, California, United States
Summary
🤩
Rockstar🎓
Top SchoolRohun Kulkarni is a robotics engineer with 10 years of experience designing and shipping intelligent, interactive robotic systems across research and industry, currently a Member of Technical Staff at Foundry Robotics after leading robotics efforts at Dexterity. He blends hands-on mechanical and firmware experience with advanced perception and ML work from his time at Stanford PAIR and open-source contributions like reproducing DenseFusion’s 6D pose estimation benchmarks. Comfortable taking concepts through iterative design to production, Rohun has repeatedly integrated vision, simulation, and manipulators to accelerate AI research and productization. He holds degrees from MIT and Stanford and is drawn to fast-paced teams with ambitious goals, often learning new tools and immediately applying them to solve practical system-level challenges.
10 years of coding experience
8 years of employment as a software developer
Bachelor of Science (BSc), Mechanical Engineering, Bachelor of Science (BSc), Mechanical Engineering at Massachusetts Institute of TechnologyMath, Science and Technology, Math, Science and Technology at DuPont Manual High SchoolMaster of Science - MS, Mechanical Engineering, Master of Science - MS, Mechanical Engineering at Stanford University
Chinese, Spanish, Hindi
Github Skills (14)
pytorch10
machine-learning10
computer-vision10
python10
modeling9
trainings9
data-set9
datasets9
evaluation9
data-management9
eval9
bash8
github-ci3
githubaction-workflow3
Programming languages (6)
Github contributions (5)
j96w/DenseFusion
Jan 2019 - Mar 2020
"DenseFusion: 6D Object Pose Estimation by Iterative Dense Fusion" code repository
Role in this project:
ML Engineer
ML EngineerContributions:23 commits, 5 PRs, 20 pushes in 1 year 2 months
Contributions summary:Rohun primarily focused on setting up the environment for training and evaluating a 6D object pose estimation model. Their contributions involved downloading and integrating datasets (YCB-Video, LineMOD), configuring training scripts, and modifying evaluation scripts. They also addressed dependencies and fixed bugs in download scripts and evaluation pipelines, making the project easier to reproduce and evaluate.
pose-estimation
j96w/MimicPlay
Sep 2023 - May 2024
"MimicPlay: Long-Horizon Imitation Learning by Watching Human Play" code repository
Contributions:1 review, 2 PRs, 11 pushes in 7 months
imitation-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.