Security Tester at BLEND Localization | Torre
Security Tester
trending_up Invest in Torre
BLEND Localization

Security Tester

BLEND Localization
Posted by
Corina Apostoiu
Emma
Emma
Emma highlights
This highlight was written by Emma’s AI. Ask Emma to edit it.
Freelance
A project
Submit your quote while applying
location_on
Remote (anywhere)
Posted 8 days ago

Responsibilities and deliverables

Test AI systems for weaknesses. BLEND is building a team of security testers for an AI red-team programme with one of our clients. Instead of testing websites or apps, you test AI chatbots and agents — finding flaws and writing up what you found. About the role: You will try to make AI systems misbehave: slipping past their rules, exposing hidden instructions, misusing their tools, or leaking data they should protect. Then you document how you did it in a clear report. It is a strong fit if you come from security testing, penetration testing, bug bounty, or ethical hacking, or if you have been experimenting with breaking AI models on your own. What you will do: Test AI chatbots and agents for exploitable weaknesses. Show real, demonstrable impact, not just a clever trick. Write clear reports: what you did, how to reproduce it, and why it matters. What we look for: Experience in security testing, penetration testing, bug bounty, or hands-on AI/LLM hacking (professional or self-directed). Good written English — the report is the main deliverable. Willingness to pass an identity check and sign an NDA. Nice to have (not required): Web penetration testing experience. Certifications such as OSCP, OSWE, or GIAC. Python or JavaScript. A Hack The Box, TryHackMe, or CTFtime profile.
This job post is closed.