Priyam Parashar
Machine Learning Engineer at Waymo
Sunnyvale, California, United States
Summary
🤩
Rockstar🎓
Top SchoolPriyam Parashar is a machine learning engineer and robotics researcher with a decade of experience building real-world, multimodal robotic systems and human-robot coordination pipelines. He spent four years at Meta FAIR Robotics integrating scene-aware action prediction (SLAP) into the widely used home-robot toolkit and refactoring memory and dialogue components for embodied agents, bridging research prototypes to production-grade code. His PhD work at UC San Diego focused on leveraging prior knowledge for plan monitoring and repair in manipulators, and his background spans mobile manipulation, 3D perception for language-conditioned tasks, and dexterous transfer learning. Comfortable across the stack—from IK solvers and data pipelines to real-time system integration—he combines rigorous academic training with hands-on engineering at scale. An underappreciated thread through his career is repeated emphasis on making learning systems robust in noisy, semi-structured real-world environments.
10 years of coding experience
11 years of employment as a software developer
University of California, San DiegoDoctor of Philosophy (Ph.D.) Artificial Intelligence Robotics Human Robot Interaction, Doctor of Philosophy (Ph.D.) Artificial Intelligence Robotics Human Robot Interaction at Georgia Institute of TechnologyBachelor of Technology (B.Tech.) with Honors Electronics and Communication Engineering, Bachelor of Technology (B.Tech.) with Honors Electronics and Communication Engineering at International Institute of Information Technology Hyderabad (IIITH)Masters in Robotics Mechatronics Robotics and Automation Engineering, Masters in Robotics Mechatronics Robotics and Automation Engineering at Carnegie Mellon University
English, Hindi
Github Skills (14)
pytorch10
machine-learning10
robotics10
python10
hdf9
data-structure9
data-structures9
computer-vision9
architecture8
ros8
architectures8
database-management7
api6
apidoc6
Programming languages (8)
Github contributions (5)
facebookresearch/home-robot
Feb 2023 - Mar 2023
Mobile manipulation research tools for roboticists
Role in this project:
ML Engineer
ML EngineerContributions:131 reviews, 30 commits, 35 PRs in 1 month
Contributions summary:Priyam primarily focused on integrating and refining the SLAP (Scene-aware, Learning-based Action Prediction) model for manipulation tasks within the home-robot framework. Their work included porting the Pinocchio IK solver for manipulation, developing HDF5-based data recording and loading environments, and integrating the SLAP data-flow. Furthermore, they implemented preprocessing functions for inference-time usage and created the action prediction input.
facebookresearch/fairo
Feb 2022 - Sep 2022
A modular embodied agent architecture and platform for building embodied agents
Role in this project:Back-end Developer
Back-end DeveloperContributions:15 reviews, 105 commits, 7 PRs in 6 months
Contributions summary:Priyam primarily focused on refactoring and modifying the `droidlet/memory` module. Their contributions involved moving and updating methods related to player data access and management, specifically `get_player_by_eid`. The user also made adjustments to the `ChatNode` class, including refactoring recent chat retrieval and integrating chat effects. These changes appear aimed at improving memory management and access within the embodied agent architecture.
agentagentsembodied-agentmodulararchitecture
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.