Where you can live
Open to people living in United States.
Listed location: Remote (USA)
Taken from the location the company listed. Confirm in the posting before you apply.
What the job is
Writes adversarial prompts to test whether AI models give real help with cyberattacks, then judges whether their malware, exploit, or attack output would actually work.
What they ask for
- Professional experience in offensive security, pentesting, red teaming, vulnerability research, malware analysis, threat intel, or incident response
- Ability to read, write, and evaluate Python, PowerShell, Bash, C/C++, or JavaScript
- Understanding of MITRE ATT&CK and OWASP
- Ability to assess functional correctness and exploitability of model-generated technical output
- Strong hands-on experience using multiple LLMs
Nice to have
- Certifications such as OSCP, OSCE, GPEN, GXPN, CRTO, CRTL, CEH
- Exploit development, reverse engineering, or binary analysis experience
- Familiarity with AI/ML attack surfaces such as prompt injection and model extraction
This is a summary written by software from the company's posting. The posting is the source.
More remote jobs at Handshake