Alexandre Amice
Cambridge, Massachusetts, United States
Summary
🤩
Rockstar🎓
Top SchoolAlexandre Amice is a final-year PhD candidate at MIT focused on turning mathematical structure into high-performance, reliable decision-making software for robotics and autonomy. Advised by Pablo Parrilo and Russ Tedrake, he specializes in semidefinite programming, sums-of-squares, and conic solver development, and has shipped C++ solvers (CCosmo) and a decomposition solver (VEGA) while contributing to Drake’s optimization and planning stack. His work spans the full decision pipeline—from modeling and solver design to low-level linear algebra—enabling faster optimal decisions in robot control and verification. An active open-source developer, he has improved core robotics teaching and tools (including contributions to the widely used underactuated course material and Drake) and interned at Boston Dynamics AI Institute, demonstrating production-minded research. With seven years of engineering experience and a track record of turning algebraic structure into scalable algorithms, he seeks industrial research roles that fuse rigorous optimization with robust software.
7 years of coding experience
3 years of employment as a software developer
Doctor of Philosophy - PhD, Electrical Engineering and Computer Science, Doctor of Philosophy - PhD, Electrical Engineering and Computer Science at Massachusetts Institute of TechnologyMaster of Science, Systems Engineering, Master of Science, Systems Engineering at University of Pennsylvania
English, French, Spanish
Stackoverflow
13reputation
77reached
0answers
1question
Github Skills (12)
machine-learning10
mathematical10
robotics10
c-language10
cprogramming-language10
python10
modeling10
optimization10
numpy9
linear-algebra9
trajectory-optimization9
drake6
Programming languages (7)
Github contributions (5)
RobotLocomotion/drake
Apr 2022 - Jan 2023
Model-based design and verification for robotics.
Role in this project:
Back-end Developer
Back-end DeveloperContributions:757 reviews, 12 commits, 130 PRs in 9 months
Contributions summary:Alexandre primarily contributed to the back-end logic of the robotics library, Drake, by implementing new features and extending existing functionalities. They added implicit dynamics binding and Pontryagin difference functionality to HPolyhedron, demonstrating expertise in control theory and optimization. The user also worked on Python bindings for rational functions, expanding their capabilities and enhancing the library's usability. They also added positive_semidefinite_constraints when calling GetAllConstraints.
roboticsdrake
RussTedrake/underactuated
Feb 2022 - Apr 2022
The course text for MIT 6.832 (and 6.832x on edX)
Role in this project:ML Engineer
ML EngineerContributions:7 reviews, 11 commits, 18 PRs in 2 months
Contributions summary:Alexandre contributed to the development and improvement of educational materials for an underactuated robotics course. Their work involved modifying and updating exercises, particularly those related to pendulum control using continuous-time value iteration and iLQR. The user implemented changes to address bugs and improve the robustness of the tests. Additionally, they worked on incorporating input limits for closed-loop controllers.
edxpythonmit
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.