Work Type
Remote
Location
India, Pakistan, Bangladesh, Sri Lanka, Nepal
Compensation
Not specified
About this opportunity
Overview
BLEND Localization is building a team of security testers for an AI red-team programme with one of its clients. In this role, you will test AI systems such as models, chatbots, and AI agents that follow instructions and use tools. The work focuses on finding weaknesses, demonstrating impact, and documenting how the behavior can be reproduced.
What You'll Do
- Test AI chatbots and agents for weaknesses, including attempts to bypass safeguards, expose hidden instructions, misuse tools, or access data they should not reveal.
- Demonstrate the real impact of an issue, not only the technique used to trigger it.
- Write clear reports explaining what you did, how to reproduce the behavior, and why it matters.
What We're Looking For
- Some experience in security testing, penetration testing, bug bounty work, or hands-on AI/LLM hacking.
- Strong written English, since reporting is the main deliverable.
- A sample of work that demonstrates your skills, such as a bug bounty profile, CVE, write-up, certification, or CTF profile.
- Willingness to complete an identity check and sign an NDA.
Nice to Have
- Web penetration testing experience.
- Certifications such as OSCP, OSWE, or GIAC.
- Some Python or JavaScript experience.
- A Hack The Box, TryHackMe, or CTFtime profile.
Application Process
Applicants complete a short form of about 10 minutes. If there is a good match, the next steps are a quick skills test followed by a hands-on practical challenge for candidates who pass.
