Research Engineer - World Models

Acceler8 Talent; San Francisco, Northern (CA, KY); On-site; USD 150,000 - 230,000; Full time

Job summary

Acceler8 Talent is seeking a Research Engineer for World Models in downtown San Francisco, onsite. The role focuses on building real-time AI gaming companions and advancing frontier AI labs.

You will engage in reinforcement learning, imitation learning, and sequential decision-making, exploring world models like Dreamer or AlphaStar. Reading and implementing cutting-edge research, training, evaluating, and shipping models are required.

Qualifications

• Experience with RL/IL or sequential decision making.
• Familiarity with world models or related architectures.
• Ability to read and implement recent research papers.

Responsibilities

• Train, evaluate, and shipping models end-to-end, not just API calls.
• Read and implement recent AI research from top labs and conferences.
• Work on world-model based agents for real-time gaming environments.

Skills

Reinforcement learning

Imitation learning

Sequential decision-making

Job description

Research Engineer - World Models - Onsite, Downtown San Francisco

Hiring for a Stealth frontier AI lab building real-time AI gaming companions

Think AI squadmates that can learn, plan, understand game worlds, and play side-by-side with humans

Looking for someone research-led with experience in:

Reinforcement learning, imitation learning, or sequential decision-making

World models like Dreamer, V-JEPA, Genie, AlphaStar, SIMA, Voyager, MineDojo, or related work

Reading and implementing recent research from top AI labs and conferences

Training, evaluating, and shipping models - not just integrating APIs

Top ML/AI publications a big plus

Backed by major AI + gaming investors, including NVIDIA