AI Red Teamer (Remote)
Handshake AI · Remote (USA)
Infrastructureremote$67k–$198k
At a glance
Highlights
- Probe frontier LLMs across safety, CBRN, cybersecurity and persuasion risks.
- Design jailbreaks and multi-turn scenarios spanning text, image, voice and agents.
- Help make frontier AI safer by finding flaws before they reach users.
Ideal candidate
Creative and curiosity-driven thinker who loves challenging AI, exploring niche internet cultures, and thinking like an adversary with strong ethical judgment to advance AI safety.
Requirements
- 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 experimentation
- Ability to engage with disturbing harmful content professionally and sustainably
- remote policy
- Remote within the USA, excluding California
Lab profile
About Handshake AI
AI data business creating expert evaluations and benchmarks for frontier AI labs.
What they build
- AI evaluations
- AI benchmarks
- Expert AI training data
Known for
- Fastest-growing AI data business
- Direct work with frontier lab researchers
- 30,000+ expert contributor network
Key facts
- Handshake AI launched in 2025
- 25M job seekers
- 1M+ employers
Posted · Last seen