Job Description

xAI is seeking a highly motivated engineer to scale up high-quality reinforcement learning data for training Grok reasoning models. The role involves designing data pipelines, innovating RL algorithms, and contributing to the end-to-end data lifecycle.

Responsibilities

• Design pipelines to scale up RL data generation and collection
• Innovate next-paradigm of RL algorithms

Requirements

• Strong engineering abilities
• Familiarity with large language model data collection
• Strong communication skills
• Work ethic and strong prioritization skills

Benefits

• No benefits