William Wong
Research Engineer at Google DeepMind
San Francisco Bay Area United States
Summary
👤
Senior🎓
Top SchoolWilliam Wong is a research engineer in the San Francisco Bay Area with 10 years of cross-domain experience spanning machine learning, reinforcement learning, robotics, backend systems, and full-stack development. Currently at Google DeepMind after graduate work at CMU, he has driven research-to-production work—ranging from risk-sensitive RL libraries and industrial cooling RL to shipping autonomous behaviors on the Amazon Astro robot. He combines academic rigor (ICML/NeurIPS/ICRA publications and workshops) with practical impact, including large performance wins in device planning and production data pipelines. An active open-source contributor, he implemented a Liars Poker game integration for DeepMind’s widely used OpenSpiel repository, reflecting an aptitude for bridging game environments and RL frameworks. Known as a self-starter who moves quickly, he brings both research depth and hands-on engineering that ships consumer-facing and research systems.
10 years of coding experience
6 years of employment as a software developer
Bachelor's degree, Computer Science, Bachelor's degree, Computer Science at University of California, BerkeleyMaster of Science - MS, Machine Learning, Master of Science - MS, Machine Learning at Carnegie Mellon University
Github Skills (9)
coregames10
python10
reinforcement-learning10
videogames10
implement10
logic10
multi-agent9
cpp9
unit-testing9
Programming languages (6)
Github contributions (5)
google-deepmind/open_spiel
Dec 2022 - Jan 2023
OpenSpiel is a collection of environments and algorithms for research in general reinforcement learning and search/planning in games.
Role in this project:
Full-stack Developer
Full-stack DeveloperContributions:16 commits, 2 PRs in 1 month
Contributions summary:William implemented the initial structure and core logic for a Python-based Liars Poker game within the open_spiel repository. Their work included creating the game state, handling actions, defining legal moves, and integrating with the OpenSpiel framework. The changes involve substantial code additions for defining game rules and dynamics as well as testing the new features. These commits demonstrate an understanding of game development within a reinforcement learning environment.
cppmultiagentgamespythondatamining
w07wong/bloomjs
Oct 2018 - Sep 2020
http://memento.ieor.berkeley.edu/bloom/Mori.html to JS
Contributions:2 PRs, 6 pushes, 3 branches in 1 year 10 months
bloomjavascriptmementoberkeleyedu
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.