Research Scientist / Engineer – Reinforcement Learning Infrastructure

Research Scientist/Engineer at Luma Labs focused on building and scaling reinforcement learning systems. This role involves designing and implementing distributed RL post-training pipelines, developing RL environments for agentic tasks, and building robust reward infrastructure to optimize model behavior.

Skills and focus areas

• reinforcement learning
• distributed systems
• policy optimization
• inference
• agentic environments
• reward systems
• verification
• large scale systems
• llm post-training
• rollout generation
• environment design
• reward infrastructure