Reinforcement Learning Engineer - Ingénieur(e) en apprentissage par renforcement
Core
Design robust simulation environments, reward structures, and policy architectures to train autonomous agents in complex, multi-sensor landscapes.
Role type
Reinforcement Learning Engineer (Simulation & Sim-to-Real)
Builds
High-fidelity 2D/3D simulation environments and RL agents for real-world deployment
Domain
Robotics, Autonomous Systems, Simulation
Deliverable
production ML models
Required skills
Reinforcement Learning algorithms (PPO, SAC, Offline RL), Python, Physics engines (MuJoCo, Bullet), 3D game engines (Unity, Unreal, Isaac Sim), Reward engineering, Domain randomization, Markov Decision Processes (MDPs), Gradient-based optimization
Preferred skills
Robotics, Imitation Learning, Online Machine Learning, Smart grids, Precision agriculture, Game development, Aerospace
Technologies
Ray Rllib, Stable Baselines3, CleanRL, Git, Unix shell, Jira, Confluence, Slack
Responsibilities
Design and tune complex reward functions to align agent behavior with product goals and safety constraints; Develop and optimize RL algorithms capable of handling high-dimensional 3D observation spaces; Analyze the "reality gap" and implement domain randomization or adaptation techniques to ensure models perform reliably in real-world scenarios; Build and maintain high-fidelity 2D/3D simulation environments that serve as the training ground for RL agents; Work with partner ML and Annotation engineers and TPMs to spec out data, simulation, and training requirements
Seniority
Mid-to-Senior, hands-on IC
