AI Security Architect – AI Red Team
C-Serv
full-time
Posted on:
Location Type: Hybrid
Location: Portland • Idaho • Nevada • United States
Visit company websiteExplore more
About the role
- Design and lead adversarial testing of LLM and AI-driven systems
- Conduct threat modelling across model, infrastructure and data layers
- Execute and oversee testing for:
- Prompt injection
- Jailbreaking
- Model exploitation
- Data leakage / extraction
- RAG system manipulation
- Translate findings into structured, audit-ready documentation
- Map vulnerabilities and remediation pathways to:
- ISO 27001 controls
- SOC 2 Trust Service Criteria
- ISO 27701 privacy controls
- ISO 27017 cloud security controls
- Partner closely with engineering, security, and compliance functions
- Present findings clearly to executive leadership
- Ensure AI security findings integrated into enterprise governance frameworks.
Requirements
- Strong understanding of adversarial machine learning
- Experience red teaming LLM or AI systems
- 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
- Systems thinker
- Curious and adversarial in mindset
- Comfortable identifying uncomfortable truths
- Autonomous and fast-moving
- Enterprise-aware, not just technically strong
- Able to operate independently under executive leadership
Benefits
- Comprehensive Private Medical Coverage
- Support for Mental Health Expenses
- Life Insurance Options
- Attractive Compensation Package
Applicant Tracking System Keywords
Tip: use these terms in your resume and cover letter to boost ATS matches.
Hard Skills & Tools
adversarial machine learningred teamingPythonthreat modellingprompt injection testingjailbreaking testingmodel exploitation testingdata leakage testingRAG system manipulationaudit-friendly documentation
Soft Skills
strong written communicationstrong verbal communicationsystems thinkingcuriosityadversarial mindsetability to present to executive leadershipautonomyfast-movingenterprise awarenessability to identify uncomfortable truths