Ai Engineer — Reinforcement Learning

AI Engineer specializing in Reinforcement Learning at Yutori. This role involves building a superhuman generalist web-agent and scaling infrastructure, data, and algorithms for large-scale distributed asynchronous reinforcement learning with multimodal LLMs in web environments. The engineer will collaborate with product engineers to translate AI capabilities into product experiences.

Skills and focus areas

• reinforcement learning
• large-scale rl
• post-training multimodal llms
• distributed systems for rl
• ml infrastructure
• gpu clusters
• networking
• nccl
• high iq
• high eq
• high agency
• high craftsmanship