Model​/Action Policy Researcher

World Model / Action Policy Researcher – Medal

Apply for the World Model / Action Policy Researcher role at Medal.

Get AI-powered advice on this job and more exclusive features.

This range is provided by Medal. Your actual pay will be based on your skills and experience — talk with your recruiter to learn more.

$/yr - $/yr

The most powerful foundation models are trained on written words. But human intelligence far exceeds language. Truly intelligent machines must move from words to worlds, and acquire the capacity to perceive, anticipate, and improvise. They need to obtain a general intuition of reality.

We embrace games as the ultimate expression of ingenuity and problem solving. General Intuition builds on the strength of Medal, the world’s largest and fastest-growing platform for gaming moments. Every year, our players capture billions of gameplay clips, each representing a unique, action-packed highlight. Across countless environments, this diversity leads to uniquely capable agentic systems.

For the past year, we’ve been pushing the frontier across:

• Agents capable of deep spatial and temporal reasoning
• World models that provide training environments for those agents, and
• Video understanding with a focus on transfer beyond games

• 5+ years of experience in deep learning research or reinforcement learning, with a focus 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 — you understand how to train models that simulate dynamics and plan actions in learned environments.
• Proficiency in reinforcement learning (RL, model-based RL, or imitation learning) and the ability to design and evaluate policy networks.
• Programming fluency in Python and deep learning frameworks such as PyTorch.
• Strong experimental skills — comfort with large‑scale training, evaluation pipelines, and managing complex datasets or simulations.
• Publications or open-source contributions in areas like world modeling, simulation learning, or agent policies are a strong plus.
• In‑person:
  Looking to hire in NYC. 5 days in the office.
• Ownership & scientific rigor:
  You see ideas through from concept to proof to deployment. You write clean, reproducible code and maintain a high bar for experimental validity.
• Performance and scaling mindset:
  You care about how research translates into production systems, with an understanding of compute efficiency, distributed training, and data bottlenecks.
• Curiosity‑driven and result‑oriented:
  You’re excited by open‑ended problems, but you also know how to define measurable goals and ship impactful systems.
• Gaming & simulation passion:
  Interest in interactive environments, physics‑based simulations, or gaming AI. Experience with Unity, Unreal Engine, or custom simulators is a plus.

• Core Research: Python, PyTorch, Num Py, Triton, and CUDA
• Backend & Infra: Kubernetes, GCP, and large‑scale training clusters
• Experimentation: We run continuous evaluation, A/B testing, and performance metrics tracking on our deployed models

• Work on cutting‑edge research that connects AI, gaming, and simulation.
• Collaborate with a passionate team that values creativity, ownership, and technical depth.
• Competitive salary, equity options, comprehensive health insurance, and 401k.
• Opportunity to see your research shape real‑world interactive experiences for millions of users.

Mid‑Senior level

Full‑time

General Business, Management, and Business Development

Industries:
Computer Games

Referrals increase your chances of interviewing at Medal by 2x