Pedro Morais is a Staff Research Scientist with 11 years of experience building machine learning, simulation, and control software for highly dynamic legged robots. Based in Portland, he has led sim-to-real breakthroughs and produced the fastest known controller for a human-size biped while at Oregon State University, and later deployed robust field-ready systems at Agility Robotics. His work spans Monte Carlo planners, deep reinforcement learning, and custom high-performance training frameworks—often implemented as open, reproducible tooling on GitHub. Now at Boston Dynamics, he applies that blend of research rigor and production engineering to dexterous manipulation for Atlas. Colleagues describe him as someone who pairs clean, modular code with aggressive performance tuning, and who deliberately optimizes for real-world reliability rather than lab-only results.
11 years of coding experience
4 years of employment as a software developer
Crescent Valley High School
BS, Computer Science, 3.9, BS, Computer Science, 3.9 at Oregon State University
Computer Science, Computer Science at Universidade Federal do Rio Grande do Sul
Contributions:6 commits, 4 pushes, 1 branch in 1 year 11 months
javascriptjacobianjavascript-demo
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.
Request Free Trial
Pedro Morais - Controls Engineer at Agility Robotics