AI Security Engineer

About the role

We are looking for an AI Security Engineer to design and implement security controls for AI systems, large language models and autonomous agents. The role blends traditional cybersecurity expertise with emerging AI‑specific threat mitigation, ensuring the confidentiality, integrity and availability of AI‑driven services.

Key responsibilities

• Design AI security architecture and conduct AI‑specific threat modeling.
• Implement defenses against prompt injection, jailbreaks and tool abuse.
• Define AI identity, authentication, authorization and access controls.
• Conduct AI security testing, adversarial testing and red‑team exercises.
• Perform AI privacy reviews covering PII, prompts, outputs and logs.
• Partner with AI Governance and Platform Engineering to strengthen security posture.
• Communicate AI‑specific risks and vulnerabilities to security leadership.
• Identify and remediate vulnerabilities and emerging AI threats.
• Train delivery teams on AI security best practices and threat patterns.

Required profile

• 5+ years of cybersecurity/AppSec experience, including 2+ years in AI/LLM/Agent security.
• Strong knowledge of LLM and agent security threats such as prompt injection, jailbreaking and data exfiltration.
• Solid foundation in IAM, network security, secure SDLC and application security.
• Experience with AI/LLM security testing and adversarial testing tools.
• Ability to stay updated on emerging AI security threats and vulnerabilities.
• Excellent communication and stakeholder‑management skills.

Required skills

• Cybersecurity and Application Security (AppSec)
• AI/LLM/Agent Security
• Prompt injection mitigation
• Jailbreak defense
• Tool abuse protection
• Identity and Access Management (IAM)
• Network security
• Secure Software Development Lifecycle (SDLC)
• Azure AI Foundry Prompt Shields / content filtering
• AWS Bedrock Guardrails
• Google Vertex AI safety controls
• NeMo Guardrails (open‑source)
• Rebuff (open‑source)
• AI privacy and data protection
• AI red‑team testing
• Adversarial testing tools