AI Red Teamer, CBRNE (Remote)
Handshake AI · Remote (USA)
Infrastructureremote$135k–$329k
At a glance
Highlights
- Probe frontier AI models for gaps in CBRNE safety guardrails.
- Craft adversarial scenarios stress-testing model defenses beyond non-expert reach.
- Test multi-turn attack chains simulating how motivated actors extract risky info.
Ideal candidate
Deep CBRNE domain expert who thinks like a sophisticated threat actor and cares about AI safety and national security. Ethically grounded, self-directed collaborator comfortable probing sensitive weapons-related content within strict guardrails.
Requirements
- Deep subject matter expertise in at least one CBRNE domain
- Strong ethical judgment and ability to think like a sophisticated threat actor
- Ability to separate adversarial thinking from personal values
- Self-directed, collaborative, and comfortable in feedback-heavy environments
- Able to engage with sensitive CBRNE-related content professionally and sustainably
- remote policy
- Remote; not hiring candidates based in 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