Эта вакансия в архиве
Посмотреть похожие вакансии ↓обновлено 2 месяца назад
Reinforcement Learning Engineer (AI)
Описание вакансии
Текст:
TL;DR
Reinforcement Learning Engineer (AI): Developing robust simulation environments and training autonomous agents with an accent on reward engineering, policy architecture, and sim-to-real strategies. Focus on implementing complex RL algorithms like PPO and SAC to navigate high-dimensional 3D landscapes for multi-sensor systems.
Location: Montréal, Canada. Must be able to attend an in-person interview at an location.
Company
is a global leader in media and entertainment, creating world-class content across film, television, streaming, and theme parks.
What you will do
- Collaborate with ML engineers and TPMs to define simulation and training requirements.
- Build and maintain high-fidelity 2D/3D simulation environments using Unity, Unreal, or Isaac Sim.
- Design and tune complex reward functions to align agent behavior with safety and product goals.
- Develop and optimize RL algorithms such as PPO, SAC, or Offline RL.
- Implement domain randomization and adaptation techniques to bridge the reality gap.
Requirements
- Graduate degree (Master’s or PhD) in Robotics, Computer Science, or AI.
- Proven experience as an RL Engineer or Research Engineer.
- Fluency in Python, Git, and Unix shell environments.
- Deep familiarity with RL frameworks like Ray RLlib, Stable Baselines3, or CleanRL.
- Experience with physics engines like MuJoCo or Bullet.
- Strong mathematical background in Markov Decision Processes and gradient-based optimization.
Nice to have
- Experience in robotics, smart grids, precision agriculture, game development, or aerospace.
Culture & Benefits
- Inclusive culture focused on attracting and developing diverse talent.
- Commitment to community service and social engagement.
- Opportunity to work on large-scale media and entertainment technology projects.