LLM Red-Teamer

micro1 is seeking skilled LLM Red-Teamers to join a high-impact project focused on the evaluation and improvement of frontier language models. You will play a critical role in shaping how next-generation AI systems learn and reason by providing high-quality, real-world input and rigorous testing.

Key responsibilities

• Develop complex, adversarial multi-turn conversations and task-based scenarios based on project specifications.
• Author precise evaluation rubrics to assess model responses against defined behavioral targets.
• Iteratively test conversations against frontier LLMs, escalating difficulty to reach quality thresholds.
• Deliver comprehensive task packages including transcripts, target behaviors, and supporting evidence.
• Validate LLM outputs by documenting model strengths and failure modes.

Requirements

• Exceptional written English skills with strong structural organization and clarity.
• Deep familiarity with large language models and the ability to identify common failure patterns.
• Proven critical thinking skills and meticulous attention to detail.
• Ability to work autonomously, interpreting complex specifications with minimal oversight.
• Background in writing-intensive or analysis-centric fields such as research, technical writing, or quality assurance.

What we offer

• Opportunity to contribute to the development of cutting-edge AI systems.
• Fully remote work environment allowing for independent contribution.
• Flexible, output-based task structure tailored to your workflow.