AI Red Teamer: Adversarial Prompts & Model Safety

We Love AI Jobs; Seattle, Northern (WA, KY); Hybride; USD 67 000 - 198 000; Plein temps

Résumé du poste

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.

Responsabilités

• 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.

Connaissances

Red teaming

Adversarial prompting

Jailbreak techniques

Prompt injection

Python

LLM APIs

Harm taxonomy

Outils

Open-source models

ChatGPT

Claude

Gemini

Description du poste

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.