15 Nov
|
Ju0026W Nexus
|
India
15 Nov
Ju0026W Nexus
India
We're looking for a red teamer who attacks AI systems for a living — LLM applications, RAG pipelines, and AI agents — and finds the holes before real attackers do. We want hands-on proof: engagements you've personally run, not just certifications or theory.
⚠️ Important — please read before applying: Candidates must not use any AI interview tools, AI assistants, or interview coaches during interviews. Anyone found using them will be flagged and removed from consideration.
What you'll work on
• Red teaming LLM applications and AI agents — prompt injection, jailbreaks, and guardrail bypass testing
• Testing RAG systems and agent tool use for data leakage and exfiltration paths
• Adversarial testing of AI features before launch, and re-testing after fixes
• Attacking the AI pipeline end-to-end — model supply chain, open-weight model provenance, sandboxing, and access control
• Network and web application penetration testing
• Writing up findings clearly,
with reproductions and fixes the engineering team can act on
What we're looking for:
• Minimum 3 years of experience in cybersecurity, with hands-on red team / offensive security work
• Experience red teaming AI and LLM systems — prompt injection, jailbreaks, agent tool-use abuse
• Hands-on experience with tools such as Burp Suite, Nmap, Metasploit, and Ghidra
• Working knowledge of the defender's side — SIEM, EDR/XDR, and how detection actually sees your attacks
• Familiarity with AI security frameworks — MITRE ATLAS, OWASP LLM Top 10, NIST / MITRE guidance
• Robust Python scripting for automation and exploit development
• At least one real engagement or incident you personally ran, end-to-end
If that's you, apply here on LinkedIn
#CyberSecurity #RedTeam #AISecurity #Hiring #RemoteJobs #InfoSec
📌 AI Cybersecurity Specialist (Red Team) (India)
🏢 Ju0026W Nexus
📍 India