Senior Research Engineer, Interactive World Models

What you'll do

• Build and optimize the continuous autoregressive serving loop for real-time video generation.
• Manage model and KV-cache states, GPU inference, and frame streaming for high-speed performance.
• Work with researchers on few-step distillation, reward fine-tuning, and action conditioning.
• Develop long-horizon spatiotemporal memory and consistency for world models.
• Lead end-to-end delivery of multi-user experiences and simulation workflows from prototype to release.
• Partner with domain teams to meet specific quality, performance, and reliability goals.
• Translate ambiguous research ideas into production-ready systems and deployed technologies.

What we're looking for

• MS or PhD in Computer Science, Electrical Engineering, or a related field (or equivalent experience).
• 5+ years of equivalent experience in applied ML or research engineering.
• Experience in video or world models, diffusion and generative modeling, model distillation, simulation, robotics, computer vision, or real-time ML systems.
• A record of advancing applied ML or ML systems through research, open-source software, patents, or deployed technology.
• Hands-on experience with Python, PyTorch, and GPU-accelerated training, inference, performance optimization, or serving.
• Research and engineering judgment to find practical solutions to open-ended problems within software and hardware constraints.
• Experience with post-training generative video models, including distillation, self-forcing, action conditioning, or long-horizon memory (preferred).
• Experience building real-time generative inference systems, GPU kernels, quantization, or technical stewardship of an open-source ML project (preferred).