← All roles

Research Scientist, Real-Time Interactivity / Inference

Reactor· Research
Apply on company site
Hybrid (San Francisco, CA)Full TimePosted 5mo ago

About the role

Research Scientist to lead real-time interactive generation methods and architecture for world models, collaborating with inference engineers and model partner teams, with opportunities to publish at top venues and influence Reactor’s real-time interactive world models platform.

Responsibilities

  • Lead a research agenda on real-time interactive generation — inference-time methods, architectural design, and where the field should go next
  • Partner closely with inference engineers to understand bottlenecks in serving real-time interactive world models and shape research
  • Work with model partner teams to gain a broad view of the interactive world model landscape, architectures, failure modes, and open problems
  • Publish and present work at top venues (NeurIPS, ICLR, ICML, CVPR, ICCV, SIGGRAPH, and equivalents)

Qualifications

  • PhD in ML, computer vision, graphics, robotics, or a related field, or equivalent practical experience
  • Track record of research in real-time or streaming video generation, autoregressive / causal video diffusion, diffusion distillation, efficient attention or state-space models for generation, or interactive controllable generation
  • Latency, memory, and model quality treated as a single problem
  • Fluent in PyTorch and/or JAX and comfortable with large-scale training and inference infrastructure
  • Real systems intuition — ability to read a profiler, reason about memory bandwidth, and talk with kernel engineers
  • Value quality over quantity in publishing; open-source work as evidence of impact

Skills

Required:Real-time / streaming video generationPyTorch
Nice to have:Autoregressive / causal video diffusionDiffusion distillationEfficient attention / state-space modelsJAX

Benefits

  • A seat on Reactor's research team with room to influence direction and lead research agenda
  • Broad exposure across field with real workloads from multiple model families
  • Close collaboration with a world-class ML inference engineering team
  • Sufficient compute to train and serve models at scale
  • Support for publishing at top conferences
  • Competitive SF salary and meaningful early equity
  • Visa sponsorship and relocation support
  • Generous health, dental, and vision coverage
Last updated Oct 15, 2026. Interested? Apply on the company site.

About Reactor

Company profileWebsite

More open roles at Reactor