Alexander Clegg
Research Engineer at Meta Robotics Studio
Hawaii, United States
Summary
🤩
Rockstar🎓
Top SchoolAlexander Clegg is a research engineer with 11 years of experience at the intersection of AI, robotics, and computer graphics, currently building simulation tools for robotics at Meta Robotics Studio. He earned a PhD in Computer Science from Georgia Tech, where his NSF-funded work and dissertation focused on modeling human and robot behavior during dressing tasks—melding physical simulation, animation, and learning. At Facebook AI Research he was a core contributor and system architect for the widely used Habitat simulator, improving scene/object loading, caching, and articulated object support. He combines deep learning (RL) and motion synthesis expertise with strong backend and systems design skills, enabling high-performance embodied AI research. Based in Hawaii, he brings practical industry software experience from enterprise work and a history of teaching and mentoring in computer graphics.
11 years of coding experience
10 years of employment as a software developer
Doctor of Philosophy (PhD) Computer Science, Doctor of Philosophy (PhD) Computer Science at Georgia Institute of Technology
Github Skills (18)
c-language10
python10
simulator10
object-oriented-programming10
cprogramming-language10
architecture9
reinforcement-learning9
3d-graphics9
simulation9
simulations9
physics9
architectures9
system9
computer-vision8
deep-learning8
Programming languages (3)
Github contributions (5)
facebookresearch/habitat-sim
Aug 2019 - Jan 2023
A flexible, high-performance 3D simulator for Embodied AI research.
Role in this project:
Back-end Developer & System Architect
Back-end Developer & System ArchitectContributions:18 releases, 660 reviews, 528 commits in 3 years 5 months
Contributions summary:Alexander primarily focused on enhancing the simulator's core functionality, particularly regarding scene and object loading. Their contributions included enabling empty scene loading with specific configuration settings and integrating support for various scene and mesh types, including MP3D meshes and articulated objects via URDF parsing. The user refactored the system's architecture by creating a scene graph, incorporating a caching mechanism for data, and introducing the concept of different *MotionType* behaviors for objects. The work demonstrates an understanding of system architecture and back-end logic in a simulation environment.
roboticsembodied-aicomputer-visionsimulation3d-simulator
facebookresearch/habitat-lab
Aug 2020 - Dec 2022
A modular high-level library to train embodied AI agents across a variety of tasks and environments.
Role in this project:Backend Developer
Backend DeveloperContributions:9 releases, 359 reviews, 155 commits in 2 years 4 months
Contributions summary:Alexander contributed to the core functionality and maintenance of the Habitat-Lab project. Their work included modifying documentation links within the simulation environment, updating the version number, and removing unused agent properties. They also upgraded the minimum Python version, fixed related bugs, and refactored code for improved functionality and compatibility. Additionally, the user updated references to YCB configs directory.
pythonembodied-aideep-reinforcement-learningsimulatorai-agents
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.