AI Red Teamer (Seattle)

We Love AI Jobs; Seattle, Northern (WA, KY); Hybrid; USD 67,000 - 198,000; Full time

Job summary

We Love AI Jobs in Seattle is seeking an AI Red Teamer (LLM Generalist) to stress-test large language models through creative prompts and multi-turn scenarios. You will probe as an adversary, test jailbreaks and prompt injections, and evaluate outputs against harm taxonomies, contributing to stronger model defenses.

Collaborate with engineers, data scientists, and researchers, review and refine prompts, and document findings to support AI safety initiatives across risk categories.

Qualifications

• Experience stress-testing large language models with adversarial prompts.
• Ability to document experiments and findings clearly for engineering teams.
• Familiarity with safety, security, and risk domains in AI.

Responsibilities

• Craft creative prompts and multi-turn scenarios to probe AI guardrails.
• Discover jailbreaks, evasion methods, and prompt injection weaknesses.
• Evaluate model outputs using structured harm taxonomies and rubrics.
• Document experiments with methods, results, and insights for teammates.
• Collaborate with engineers, data scientists, and researchers to strengthen defenses.

Skills

Red teaming

Adversarial prompting

Jailbreak techniques

Prompt injection

Python

LLM APIs

Harm taxonomy

Tools

Open-source models

ChatGPT

Claude

Gemini

Job description

# AI Red Teamer (Seattle)HandshakeSeattle, WAFull-time$66,560 – $197,600 / yearAI tools:ChatGPTClaudeGeminiUpload your resume once and Scout applies for youApply with ScoutShare this job:LinkedInXSave imageThe AI Red Teamer tests large language models by creating adversarial prompts and scenarios across safety, security, and other risk areas. The role documents and scores model behavior, then shares findings with engineers, data scientists, and researchers to help strengthen defenses.* Contract* On-site### Skills and expertiseLLM red teamingAdversarial promptingJailbreak techniquesPrompt injectionModel evaluationHarm taxonomy scoringPythonLLM APIs### Key responsibilities* Create adversarial prompts and multi-turn scenarios to test model safeguards across diverse risk categories.* Score model responses using structured harm taxonomies and document experiments and findings.* Collaborate with engineers, data scientists, and researchers to identify vulnerabilities and strengthen model defenses.## How this job comparesCompared with 90 open mid-level research jobs on October 10, 2026.Pay: This job pays $67K to $198K a year. The 32 open mid-level research jobs that publish US pay start at $199K on average, so this job starts about 67% lower.Similar open jobs: We Love AI Jobs lists 90 open mid-level research jobs at 53 companies.Remote work: This job is on site. 12 of the 90 mid-level research jobs (13%) are remote.AI in this role: High. AI is the core of the work: building, training or deploying AI systems. The role is centered on hands-on testing of language models, including probing their safeguards and evaluating their responses. The posting names ChatGPT, Claude, and Gemini as models candidates should have used.## Full descriptionAI Red Teamer (LLM Generalist)Location: Seattle, WA (candidates must reside in the Seattle metro area or be willing to relocate prior to start)Employment type: W-2, hourly, employed through TCWGlobalHours: 40 hours per weekAbout the RoleAs an AI Red Teamer, you will stress-test large language models by intentionally trying to break them. Rather than checking whether an answer is correct, you will design creative, adversarial prompts that expose vulnerabilities: unsafe content, bias, broken guardrails, hallucinations, prompt injection weaknesses, and unexpected behaviors. Your work directly supports AI safety and model robustness for leading research labs.This is a generalist red teaming role. You will probe models across the full spectrum of risk categories, including content safety, CBRN (chemical, biological, radiological, nuclear), cybersecurity, persuasion and influence operations, child safety, self-harm, over-companionship, and regulatory compliance. Red teaming may span text, image, voice, and agentic model capabilities depending on project needs.This role requires creativity, curiosity, and an ability to think like an adversary while operating with strong ethical judgment.Day-to-Day Responsibilities• 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 (see Content Warning below)• Stay current on jailbreaks, attack methods, and evolving model behaviorsDesired CapabilitiesCore• Strong hands-on experience using multiple LLMs (ChatGPT, Claude, Gemini, open-source models, etc.)• Intuition for crafting adversarial prompts; familiarity with jailbreak or evasion techniques is a strong plus• Creative, adversarial problem-solving skills• Clear and thoughtful written communication• Strong ethical judgment and the ability to separate adversarial thinking from personal values• Self-directed, collaborative, and comfortable in feedback-heavy environments• Curiosity, persistence, and comfort with frequent failure in experimentationNice to Have• 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.)You Will Thrive Here If• You treat every model response as a hypothesis to challenge