Red Teaming & Generative AI Analyst

About the role

We are seeking a Red Teaming & Generative AI Analyst to evaluate the safety of cutting‑edge AI models. You will work with provided guidelines and safety taxonomies to design prompts, test model behavior, and flag unsafe or non‑compliant outputs.

Key responsibilities

• Interact with generative AI models using project‑provided safety taxonomies and attack‑vector guidance.
• Create and evaluate prompts that probe model behavior across safety‑related categories.
• Identify and document where model responses become unsafe, inconsistent, or otherwise problematic.
• Review multimodal content (text, image, audio, video) as required by the workflow.
• Apply detailed guidelines consistently during high‑volume production sprints.
• Conduct self‑reviews, flag ambiguous guidelines or tooling issues, and participate in calibration and quality‑review sessions.
• Maintain readiness to pivot quickly between different red‑teaming runs.

Required profile

• Native‑level or near‑native English proficiency with excellent written communication.
• Work authorization for the United States.
• Strong creative writing ability and comfort constructing varied prompts.
• Experience with red‑teaming, safety data annotation, content moderation, QA, or AI model evaluation (preferred).
• Attention to detail, critical thinking, and ability to handle sensitive or policy‑relevant content.
• Interest in generative AI, AI safety, and large language models.
• Bachelor’s degree or equivalent practical experience (preferred).

Required skills

What we offer

• W2 full‑time employment (40 hours/week).
• Hourly rate of $47.44.
• Remote work with the option to work onsite in selected cities.