AI Security Staff Engineer – AI Red Team

About the role

We are building an elite AI Red Team to stress‑test and harden enterprise‑scale AI products deployed for large organizations. This production‑focused role sits at the intersection of adversarial machine learning, enterprise security architecture, and governance.

Key responsibilities

• Design and execute structured red‑team engagements across multiple AI systems.
• Develop adversarial testing for LLMs and AI‑driven applications, including prompt injection, jailbreaking, model exploitation, data leakage, and RAG manipulation.
• Conduct threat modelling across model, infrastructure, and data layers.
• Translate findings into audit‑ready documentation and map vulnerabilities to ISO 27001, SOC 2, ISO 27701, and ISO 27017 controls.
• Partner with engineering, security, and compliance teams to integrate findings into enterprise governance frameworks.
• Present technical risk and remediation pathways clearly to executive leadership.

Required profile

• Deep technical expertise in adversarial machine learning and red‑team operations on LLMs or AI systems.
• Strong understanding of AI deployment architectures (RAG, APIs, vector databases, fine‑tuning pipelines).
• Proficiency in Python and experience working within ISO 27001 environments.
• Familiarity with SOC 2 Trust Service Criteria, ISO 27701 privacy extensions, and ISO 27017 cloud security controls.
• Ability to produce clear, structured, audit‑friendly documentation and present findings to senior executives.

Required skills

• Adversarial machine learning
• LLM red‑team testing
• AI deployment architectures (RAG, APIs, vector DBs, fine‑tuning pipelines)
• Python programming
• ISO 27001
• SOC 2 Trust Service Criteria
• ISO 27701
• ISO 27017

What we offer

• Comprehensive private medical coverage
• Attractive compensation package