Build RL environments, verifiers, fine-tuning pipelines, and eval systems for frontier AI agents at Labelbox. Requires deep RL post-training experience (SFT + RL methods), strong Python/systems engineering, and the ability to ship production infrastructure at high velocity.
Build and scale eval systems, fine-tuning pipelines, agent-first infrastructure, and data platforms that power frontier AI labs at Labelbox. Requires full-stack prototyping expertise, strong architecture judgment, daily use of coding agents, and deep TypeScript/Python proficiency (7+ years implied by Staff level).
Builds and maintains sandboxed, reproducible RL environments for AI agent training, including terminal, browser, and tool-augmented setups. Requires 2+ years Python/systems engineering, containerization, and RL concepts understanding.
Build RL environments, verifiers, fine-tuning pipelines, and eval systems for frontier AI agents at Labelbox. Requires deep RL post-training experience (SFT + RL methods), strong Python/systems engineering, and the ability to ship production infrastructure at high velocity.
Build and scale eval systems, fine-tuning pipelines, agent-first infrastructure, and data platforms that power frontier AI labs at Labelbox. Requires full-stack prototyping expertise, strong architecture judgment, daily use of coding agents, and deep TypeScript/Python proficiency (7+ years implied by Staff level).
Builds and maintains sandboxed, reproducible RL environments for AI agent training, including terminal, browser, and tool-augmented setups. Requires 2+ years Python/systems engineering, containerization, and RL concepts understanding.