Alessandro Palmas
Senior AI ML Research Engineer at LawZero
Montreal, Quebec, Canada
Summary
👤
Senior🎓
Top SchoolAlessandro Palmas is a senior AI/ML research engineer with 11 years of hands-on experience building foundation models, reinforcement learning systems, and simulation platforms for aerospace, defense, robotics, and AAA gaming. He bridges deep research and production engineering—having founded and exited DIAMBRA, led distributed RL pipelines at Ubisoft Montréal, and now working on truthful, transparent, safe-by-design models at LawZero under Yoshua Bengio. His expertise spans SFT, RLHF/RLAIF, DPO, multi-agent and curriculum learning, and high-fidelity simulation for embodied agents, with a track record of deploying models to embedded devices and large-scale cloud systems. Alessandro combines strong academic grounding in aerospace and space engineering with product-focused delivery, having authored RL book chapters and shipped libraries for RL, simulation, and geometry processing. Notably, he has repeatedly moved prototypes into operational use—from drone autonomy and space debris tracking to competitive RL platforms—demonstrating a rare blend of theoretical rigor and systems-level execution.
10 years of coding experience
9 years of employment as a software developer
Master of Science (MSc), Space Engineering, 110/110 Cum Laude, Master of Science (MSc), Space Engineering, 110/110 Cum Laude at Politecnico di MilanoMultidisciplinary International Program, V Cycle, Multidisciplinary International Program, V Cycle at Alta Scuola PolitecnicaMaster of Science (MSc) by Research, Space Engineering, Master of Science (MSc) by Research, Space Engineering at The University of GlasgowMaster of Science (MSc), Aerospace Engineering, 110/110 Cum Laude, Master of Science (MSc), Aerospace Engineering, 110/110 Cum Laude at Politecnico di Torino
Italian, English, c++, python, French, Spanish
Github Skills (41)
face10
artificial-intelligence10
machine-learning10
reinforcement-learning10
deep-learning10
deep-reinforcement-learning10
optimization10
parallel9
pytorch9
java9
python9
ray9
hyperparameter-optimization8
tensorflow8
llm-inference8
Programming languages (8)
Github contributions (5)
diambra/agents
Apr 2020 - Mar 2023
Example Agents for DIAMBRA Arena Environments
Contributions:11 reviews, 958 commits, 49 PRs in 2 years 11 months
reinforcement-learningagentsdeep-reinforcement-learningarenaenvironments
diambra/arena
Feb 2021 - Jan 2023
DIAMBRA Arena: a New Reinforcement Learning Platform for Research and Experimentation
Contributions:63 reviews, 674 commits, 86 PRs in 1 year 11 months
experimentationlearning-platformdeep-learningreinforcement-learningtournaments
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.