Security / Red-Team Lead (AI Security)

Role overview

Birbal AI is hiring an experienced Security / Red-Team Lead to drive AI security testing and adversarial evaluations for enterprise AI products. This role focuses on assessing the resilience of Large Language Models (LLMs), RAG pipelines, and AI-powered solutions against prompt injection, jailbreak attempts, and other offensive techniques.

What you will do

• Plan and lead security assessments and red-team exercises for AI applications.
• Evaluate enterprise AI systems for weaknesses through penetration testing and adversarial testing methods.
• Test and analyze LLMs, RAG systems, and AI-enabled applications for prompt injection, jailbreak, and related abuse paths.
• Review AI and cloud security posture through threat modeling, risk analysis, and security architecture assessments.
• Perform application security testing across web and API services, including secure coding review and vulnerability assessment.
• Assess network security controls such as segmentation, firewalls, IDS/IPS, secure VPNs, and offensive testing of networked systems.
• Lead and mentor security team members while coordinating complex red-team engagements end to end.
• Work on hardening AI systems, including machine learning adversarial defense and secure deployment of LLMs or agentic AI solutions.
• Support cloud security, IAM, and security automation/monitoring initiatives.

What we are looking for

• 7 to 9 years of background in cybersecurity, penetration testing, or red teaming.
• Strong command of cybersecurity and information security concepts, especially threat modeling, risk assessment, and security architecture for AI and cloud environments.
• Practical experience in application security, including secure coding practices, web/API penetration testing, and vulnerability assessment for AI-enabled products.
• Good knowledge of network security, including segmentation, firewall and IDS/IPS configuration, secure VPNs, and offensive testing of connected systems.
• Demonstrated ability to lead teams, mentor security professionals, and manage sophisticated security engagements.
• Experience with adversarial machine learning attacks, AI hardening, and secure rollout of LLM or agentic AI systems.
• Familiarity with major cloud platforms, identity and access management, and security automation and monitoring tools.
• Relevant certifications such as OSCP, OSCE, CREST, CISSP, or equivalent hands-on offensive security experience.

Additional information

This is a full-time onsite position based in Abu Dhabi, Abu Dhabi Emirate, United Arab Emirates.