AI Security Analyst: Frontier Model Vulnerability Hunter

Alignerr Corp.; Johannesburg; Teletrabalho; ZAR 1 363 000 - 2 726 000; Tempo parcial

Vantagens oferecidas por esta oferta de emprego

Fully remote

Flexible schedule

Freelance autonomy

Meaningful, task-based work

Resumo da oferta

Alignerr is seeking AI Security Analysts to probe frontier models, uncover vulnerabilities, and help ensure cutting‑edge AI remains safe and reliable. This fully remote, flexible hourly contract role is built for security professionals who are curious about how modern AI systems can be exploited — and how to stop it.

You'll analyze AI/LLM security scenarios, investigate prompt injection and data leakage, and apply threat modeling to emerging AI technologies.

Qualificações

• Background in cybersecurity, information security, or a related technical field.
• Solid understanding of modern threat modeling, attack surfaces, and adversarial thinking.
• Genuinely curious about how AI systems are built, deployed, and potentially exploited.
• Analytical and precise approach to complex systems and documenting findings clearly.

Responsabilidades

• Analyze AI and LLM security scenarios to understand model behavior under adversarial or unexpected conditions.
• Investigate prompt injection, data leakage, model abuse, and system misuse cases in realistic settings.
• Classify security vulnerabilities and recommend mitigations based on impact and likelihood.
• Apply threat modeling frameworks to emerging AI technologies and deployment contexts.
• Evaluate and improve AI system behavior to remain safe, aligned, and resilient against attack.

Conhecimentos

Threat modeling

Adversarial thinking

Independent work

Written communication

Ferramentas

Penetration testing

Red teaming

Vulnerability research

LLMs familiarity

Descrição da oferta de emprego

Alignerr is seeking AI Security Analysts to probe frontier models, uncover vulnerabilities, and help ensure cutting‑edge AI remains safe and reliable. This fully remote, flexible hourly contract role is built for security professionals who are curious about how modern AI systems can be exploited — and how to stop it.

You'll analyze AI/LLM security scenarios, investigate prompt injection and data leakage, and apply threat modeling to emerging AI technologies.