AI Red Teamer, Cybersecurity (Remote)
Handshake AI · Remote (USA)
Infrastructureremote$135k–$260k
At a glance
Highlights
- Test AI models across full cyber kill chain for dangerous assistance gaps.
- Probe dual-use boundaries from malware to exfiltration via adversarial prompts.
- Shape AI safety benchmarks with frontier labs at massive scale.
Ideal candidate
Seasoned offensive-security thinker who thinks in kill chains and cares deeply about AI safety. You love breaking systems to understand real-world risk and collaborating to harden frontier models responsibly.
Requirements
- Deep cybersecurity expertise to judge if exploits and payloads would work in real environments
- Experience designing adversarial prompts across reconnaissance through exfiltration
- Ability to evaluate model-generated malware, exploits and attack tooling for functional correctness
- Comfort engaging with offensive cybersecurity content professionally and responsibly
- remote policy
- Remote within the United States (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