World Model / Action Policy Researcher
$133,000–$133,000 year
On-site · New York City, New York, United States or Genève, Geneva, Switzerland
Job Summary
Looking for a World Model / Action Policy Researcher with expertise in deep learning and reinforcement learning, particularly in embodied agents and simulation environments. Candidates should possess strong skills in representation learning, generative modeling, and reinforcement learning. Required programming skills include proficiency in Python and deep learning frameworks like PyTorch. This role emphasizes experimental rigor, high standards for validity, and a performance-oriented mindset. The ideal candidate is passionate about gaming, simulations, and translating research into production systems.
Required Qualifications
- 5+ years of experience in deep learning research or reinforcement learning, focusing on embodied agents or simulation environments
- Strong foundation in representation learning and generative modeling, particularly using architectures such as diffusion models, VAEs, and transformers applied to video
- Experience with world models and predictive control
- Proficiency in reinforcement learning (RL, model-based RL, or imitation learning)
- Programming fluency in Python and deep learning frameworks such as PyTorch
- Strong experimental skills and comfort with large-scale training, evaluation pipelines, and managing complex datasets or simulations
- Ownership & scientific rigor with clean, reproducible code and high standards for experimental validity
- Performance and scaling mindset with knowledge of compute efficiency, distributed training, and data bottlenecks
- Curiosity-driven and result-oriented mindset
Desired Qualifications
- Publications or open-source contributions in areas like world modeling, simulation learning, or agent policies
- Experience with Unity, Unreal Engine, or custom simulators
Apply with one swipe on Sorce. We auto-fill applications and apply on your behalf — no cover letters, no 40-minute forms.
Hiring someone like this?
Get your role in front of qualified candidates on Sorce.