Red Teaming & Generative AI Analyst (Remote, USA)

About the role

We are looking for a Red Teaming & Generative AI Analyst to support safety evaluation of cutting‑edge generative AI models. You will work directly with AI systems, design and test prompts, and pinpoint where model outputs diverge from defined safety expectations.

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 unsafe, non‑compliant, inconsistent, or otherwise problematic model responses.
• Document breakability, effort level, point of failure, and category alignment for each issue.
• Review multimodal content (text, image, audio, video) as required by the workflow.
• Apply detailed guidelines consistently across high‑volume production sprints.
• Use sound judgment on ambiguous, edge‑case, or policy‑sensitive outputs.
• Self‑review work for accuracy and alignment with project expectations.
• Flag unclear guidelines, tooling issues, or recurring model behavior patterns.
• Participate in calibration, feedback, and quality‑review sessions to improve consistency.
• Maintain readiness to pivot quickly between different red‑teaming runs.

Required profile

• Native‑level or near‑native English proficiency with excellent written communication.
• Strong creative writing ability and comfort constructing varied prompts.
• Work authorization for the United States.
• Experience with red teaming, safety data annotation, content evaluation, moderation, QA, or AI model evaluation (preferred).
• Attention to detail and ability to follow complex project guidelines.
• Critical thinking skills for evaluating open‑ended model responses.
• Comfort working with sensitive, adult, NSFW, or policy‑relevant content when required.
• Interest in generative AI, AI safety, large language models, or emerging AI technologies.
• Ability to work quickly and accurately during short production windows.
• Bachelor’s degree or equivalent practical experience (preferred).

Required skills

• Prompt engineering and creative writing for AI testing.
• Familiarity with safety taxonomies, policy guidelines, evaluation rubrics, and defect categories.
• Experience reviewing multimodal AI outputs (text, image, audio, video).
• QA/testing experience in AI, data operations, content review, or annotation environments.

What we offer

• W2 full‑time employment (40 hours/week).
• Hourly rate of $33.16.
• Remote work with the option to work onsite in selected cities.