Open Positions
BLEND is building a pool of AI red-team specialists for a client working on generative AI models and agentic systems. The work is adversarial testing: probing models and agent workflows for prompt injection, jailbreaks, unsafe tool use, data leakage and guardrail failures, then documenting what you found and how you found it. If you already completed and passed the practical test on the external platform through our earlier “AI Red-Team” posting, there's no need to apply again — you're already in the client's pool.
The practical test is paid: you receive $25 once your report is approved by the client.
How the process runs:
You complete a short questionnaire about your security background, around 10 minutes.
If your answers meet the requirements, the practical test opens straight away: you register yourself on an external security platform, work through six AI agent security levels and upload a written report here, within 48 hours.
Our team reviews your report first. If something is missing, we tell you what to fix before it goes to the client.
The client makes the final decision. If you pass, BLEND pays you $25.
You then complete identity verification (KYC), sign the NDA and Project Addendum, and join a weekly onboarding session with the client.
What to know before you enroll:
Paid project work is already running, and new people are onboarded every week. Passing places you in the client's pool; the amount of work depends on the client's needs and isn't guaranteed.
Our team reviews your report first, and the client makes the final decision. In most cases we can't share why an individual report was rejected by the client.
Written and spoken English is required — all briefs, reports and communication are in English.
We expect responsiveness. Candidates who do not reply within the reminder window lose their place.