AI Red Teamer (LLM Generalist)

📋 Description

• Stress-test LLMs by designing adversarial prompts.
• Probe models across risk areas: safety, bias, guardrails.
• Document experiments: what you tried and what you found.
• Collaborate with engineers, data scientists, and researchers.
• Evaluate model outputs against harm taxonomies and severity rubrics.
• Review and refine adversarial prompts with teammates.

🎯 Requirements

• Hands-on experience with multiple LLMs (ChatGPT, Claude, Gemini, open-source).
• Craft adversarial prompts; jailbreak/evasion is a plus.
• Creative, adversarial problem-solving skills.
• Clear, thoughtful written communication.
• Strong ethical judgment; separate adversarial thinking from values.
• Self-directed, collaborative, and comfortable in feedback-heavy environments.

🎁 Benefits

• Shape AI safety at scale with global impact.
• Partner with world-class AI labs and top institutions.
• Collaborate with engineers, data scientists, researchers.
• Work on frontier AI data at scale.
• Join Handshake AI and grow in a fast-moving company.
• Be part of a mission-driven team redefining careers.