Member of Technical Staff, Generative Policies

We are a shared‑infrastructure provider that makes expensive robotics hardware available to the wider research community on a pay‑per‑use basis. As a Member of Technical Staff, Generative Policies you will join the team that builds and evaluates policy‑based control on this platform. You will train diffusion and flow‑matching policies from demonstration data, tune action representation and chunking on real robots, condition policies on visual history, proprioception and language, select sampling strategies that keep action multimodality within the control budget, and implement recovery mechanisms for off‑distribution states. The role requires proven experience with generative policies on real hardware, solid knowledge of generative modelling for sequential decision problems, a record of publications in top machine‑learning or robotics venues (or equivalent experience), fluency in Python and PyTorch, and hands‑on work with JAX or Rust as well as GPU‑accelerated simulation tools such as Isaac Lab, Newton, mjlab or Genesis. What the role asks for: - Experience training and evaluating generative policies on real hardware - Knowledge of generative modelling for sequential decision problems - Publications in top ML or robotics venues (or equivalent) - Fluency in Python and PyTorch - Experience with JAX or Rust - Experience with GPU‑accelerated simulation tools (Isaac Lab, Newton, mjlab, Genesis)