AI Security Researcher

Hello everyone! 👋 Looking for an AI Security Researcher for an international AI Security project (part-time).

This is not a classic Pentester or Red Team Engineer position. The main task is to create complex, but realistic and verifiable security scenarios where LLM models fail due to reasoning deficiencies, rather than ambiguous instructions or environment limitations.

What we expect: — 5+ years of experience in Offensive Security / Application Security / Web Penetration Testing — practical experience in AI Red Teaming / LLM Security — research mindset and interest in finding new attack scenarios, not just reproducing known techniques — fluent spoken English (B2+)

Format: — part-time (5–20 hours per week) — B2B, payment in USD — location strictly outside the Russian Federation / outside the Republic of Belarus

If you are interested or know a suitable specialist — write to direct messages 🙌