Work Type
Remote
Location
Global
Compensation
Not specified
About this opportunity
Overview
BLEND is building a fully remote team of security testers for an AI red-team programme with one of its clients. The work focuses on testing AI systems rather than traditional websites or apps, including models, chatbots, and AI agents that follow instructions and use tools. Candidates from anywhere in the world are welcome to apply.
What You'll Do
- Test AI chatbots and agents for weaknesses, including bypassing safeguards, extracting hidden instructions, misusing tools, and attempting to expose sensitive data.
- Demonstrate practical impact, not just novel tricks.
- Document findings clearly, including what was done, how to reproduce it, and why it matters.
Requirements
- Some experience in security testing, penetration testing, bug bounty, or hands-on AI/LLM hacking.
- Strong written English, as reporting is the main deliverable.
- A portfolio item that demonstrates relevant skills, such as a bug bounty profile, CVE, write-up, certification, or CTF profile.
- Willingness to complete an identity check and sign an NDA.
Preferred Qualifications
- Web penetration testing experience.
- Certifications such as OSCP, OSWE, or GIAC.
- Basic Python or JavaScript knowledge.
- Profiles on Hack The Box, TryHackMe, or CTFtime.
