AI Red Teamer (Remote)

Overview

As an AI Red Teamer, you will stress-test large language models by intentionally trying to break them, designing adversarial prompts that expose unsafe content, bias, broken guardrails, hallucinations, prompt injection weaknesses and unexpected behaviors.

What you'll do

• Craft creative prompts and multi-turn scenarios to stress-test AI guardrails across diverse risk categories
• Discover ways around safety filters, restrictions and defenses using jailbreak, evasion and prompt injection techniques
• Explore edge cases to provoke disallowed, harmful or incorrect outputs
• Evaluate and score model responses against structured harm taxonomies and severity rubrics
• Document experiments clearly, including what you tried, why you tried it and what it revealed
• Review and refine adversarial prompts generated by other team members
• Contribute to harm taxonomy development, calibration exercises and inter-rater reliability work
• Collaborate with engineers, data scientists and researchers to share findings and strengthen defenses
• Work with potentially disturbing content on a regular basis
• Stay current on jailbreaks, attack methods and evolving model behaviors

Nice to have

• Familiarity with jailbreak or evasion techniques
• Familiarity with Python or other scripting languages
• Experience working with LLM APIs or evaluation tooling
• Comfort with structured data annotation and rubric-based scoring
• Prior work in trust and safety, content moderation, QA or security research
• Subject matter expertise in any high-risk domain (cybersecurity, chemistry, biology, medicine, law, finance, etc.)

Details

• Location: Remote (USA)
• Employment type: W-2, hourly, employed through TCWGlobal
• Hours: 40 hours per week
• Content warning: regular and deliberate exposure to violence, self-harm, hate speech, sexually explicit material and child safety scenarios
• Not open to candidates residing in California