Senior RL Engineer - Ingénieur(e) principal(e) en apprentissage par renforcement
Montreal
Workplace: HybridFull timeFunction: Solutions Engineering & Sales EngineeringEducation: mastersSkills: ["Cross-functional collaboration","Strong mathematical background","Debugging","Attention to detail","Precision","Ability to analyze and adapt"]Design and build high-fidelity 2D/3D simulation environments to train reinforcement learning agents for complex, multi-sensor scenarios. You’ll collaborate with ML, annotation, and TPM partners to define data and training requirements; engineer reward functions aligned to product goals and safety constraints; implement and optimize RL algorithms (e.g., PPO, SAC, Offline RL); and improve sim-to-real performance via domain randomization/adaptation.
Loading
Loading job details...
Preparing the role view and application actions.

