NBCUniversal

NBCUniversal

Reinforcement Learning Engineer - Ingénieur(e) en apprentissage par renforcement

Montréal, QC, Canada

Sponsorship not specifiedDetected 22 days ago
PythonAlgorithmsGitLinuxMachine LearningJiraConfluenceRoboticsUnityUnreal EngineEpicResearchCollaborationPrecision Agriculture

About the role

  • NBCUniversal is one of the world's leading media and entertainment companies.
  • NBCUniversal is a subsidiary of Comcast Corporation.
  • Visit www.nbcuniversal.com for more information.

Responsibilities

  • Cross-Functional Coordination: Work with partner ML and Annotation engineers and TPMs to spec out data, simulation, and training requirements.
  • Environment Design: Build and maintain high-fidelity 2D/3D simulation environments (using tools like Unity, Unreal, or Isaac Sim) that serve as the training ground for RL agents.
  • Reward Engineering: Design and tune complex reward functions that align agent behavior with product goals and safety constraints.
  • Algorithm Implementation: Develop and optimize RL algorithms (e.g., PPO, SAC, or Offline RL) capable of handling high-dimensional 3D observation spaces.
  • Sim-to-Real Strategy: Analyze the "reality gap" and implement domain randomization or adaptation techniques to ensure models perform reliably in real-world scenarios.
  • We create world-class content, which we distribute across our portfolio of film, television, and streaming, and bring to life through our global theme park destinations, consumer products, and experiences.
  • We own and operate leading entertainment and news brands, including NBC, NBC News, NBC Sports, Telemundo, NBC Local Stations, Bravo, and Peacock, our premium ad-supported streaming service.
  • We champion an inclusive culture and strive to attract and develop a talented workforce to create and deliver a wide range of content reflecting our world.

Requirements

  • Experience with physics engines (MuJoCo, Bullet) or 3D game engines.
  • Familiarity with collaborative tools such as Jira/Confluence, Slack, a Git server, and an experiment tracking framework.
  • You can submit your request to AccessibilitySupport@nbcuni.com.
  • Technical Proficiency:
  • Physics & 3D Engines: Experience with physics engines (MuJoCo, Bullet) or 3D game engines.

Skills

  • Fluency with Python, Git, and the Unix shell.
  • Expérience avec des frameworks tels que Ray RLlib, Stable Baselines3 ou CleanRL.

Benefits

  • We are seeking a Reinforcement Learning Engineer with experience manipulating virtual environments to train autonomous agents.

Company info

  • Our impact is rooted in improving the communities where our employees, customers, and audiences live and work.

Visa & Work Authorization

  • ithout regard to race, color, religion, creed, gender, gender identity or expression, age, national origin or ancestry, citizenship, disability, sexual orientation, marital status, pregnancy, veteran status, membership i

This listing is sourced directly from NBCUniversal's careers page and normalized into a canonical job model.