Moonlake, based in San Francisco, is building the next generation of agentic model training for interactive worlds. We are seeking a full-time Member of Technical Staff to lead reinforcement learning infrastructure and post-training for multimodal agents across complex digital and physical environments.
You will work with the research team to improve guidance, reward design, and scalable evaluation, and to deploy reliable systems across multi-GPU clusters.
#J-18808-Ljbffr
We invite applications for the Member of Technical Staff: Agentic ML & RL Infrastructure position located in San Francisco, CA, United States.
We appreciate your interest in this position.
Join Moonlake and contribute to our ongoing work.
Take a moment to read everything above and see whether this role is right for you.
This posting is for the Member of Technical Staff: Agentic ML & RL Infrastructure role at Moonlake, based in San Francisco, CA, United States.