AI Security Consultant - AI Red Team

C-Serv • Vancouver, BC

2d

About The Position

We are building an AI Red Team to conduct adversarial testing against production AI systems. This role involves identifying vulnerabilities such as prompt injection, jailbreaking, model exploitation, RAG manipulation, and data extraction. The primary goal is to translate these findings into actionable insights for executive teams and auditors, mapped to relevant control frameworks like ISO 27001, SOC 2, ISO 27701, and ISO 27017. This position is for individuals who can bridge the gap between technical AI risks and enterprise governance.

Requirements

• Personally run red team engagements against LLM or AI-driven systems in production.
• Understand AI system architectures (RAG pipelines, vector databases, fine-tuning workflows, API architectures) to identify weaknesses.
• Fluent in Python for building or adapting testing tools.
• Comfortable working within ISO 27001 or SOC 2 environments.
• Ability to map AI vulnerabilities to control gaps.
• Ability to present findings to executives and ensure understanding of their importance.
• Strong understanding of adversarial machine learning.
• Deep familiarity with AI deployment architectures (RAG, APIs, vector DBs, fine-tuning pipelines).
• Strong Python proficiency.
• Experience working within ISO 27001 environments.
• Practical knowledge of SOC 2 Trust Service Criteria.
• Understanding of ISO 27701 privacy extensions.
• Familiarity with ISO 27017 cloud security controls.
• Ability to map technical findings to control frameworks.
• Ability to produce clear, structured, audit-friendly documentation.
• Comfortable presenting technical risk to executive audiences.
• Strong written and verbal communication skills.

Responsibilities

• Lead adversarial testing against production AI systems.
• Perform prompt injection, jailbreaking, model exploitation, RAG manipulation, and data extraction.
• Translate security findings into actionable insights for executive teams and auditors.
• Map security findings to ISO 27001, SOC 2, ISO 27701, and ISO 27017 control frameworks.
• Develop or adapt testing tooling using Python.
• Present technical risks to executive audiences.

Benefits

• Comprehensive Private Medical Coverage
• Support for Mental Health Expenses
• Life Insurance Options
• Attractive Compensation Package

What This Job Offers

• Job Type: Full-time
• Career Level: Principal
• Education Level: No Education Listed