The OpportunityWe are building an elite AI Red Team to stress-test and harden enterprise-scale AI products deployed to some of the world's largest organizations.
This is not a theoretical research role.
This role sits at the intersection of adversarial machine learning, enterprise security architecture, and governance. You will lead the design and execution of structured red team engagements across multiple AI systems — and translate technical risk into enterprise-aligned assurance.
If you have ever been frustrated watching AI risk findings remain stuck in a slide deck with no operational impact, this role is designed to change that.
What You'll DoDesign and lead adversarial testing of LLM and AI-driven systemsConduct threat modelling across model, infrastructure and data layersExecute and oversee testing for:Prompt injectionJailbreakingModel exploitationData leakage / extractionRAG system manipulationTranslate findings into structured, audit-ready documentationMap vulnerabilities and remediation pathways to:ISO 27001 controlsSOC 2 Trust Service CriteriaISO 27701 privacy controlsISO 27017 cloud security controlsPartner closely with engineering, security, and compliance functionsPresent findings clearly to executive leadershipThis role ensures AI security findings integrated into enterprise governance frameworks.
Requirements
What We're Looking ForCore Technical DepthStrong understanding of adversarial machine learningExperience red teaming LLM or AI systemsDeep familiarity with AI deployment architectures (RAG, APIs, vector DBs, fine-tuning pipelines)Strong Python proficiencyEnterprise Security & Governance FluencyExperience working within ISO 27001 environmentsPractical knowledge of SOC 2 Trust Service CriteriaUnderstanding of ISO 27701 privacy extensionsFamiliarity with ISO 27017 cloud security controlsAbility to map technical findings to control frameworksCommunication & DocumentationAbility to produce clear, structured, audit-friendly documentationComfortable presenting technical risk to executive audiencesStrong written and verbal communication skillsWho You AreSystems thinkerCurious and adversarial in mindsetComfortable identifying uncomfortable truthsAutonomous and fast-movingEnterprise-aware, not just technically strongAble to operate independently under executive leadershipYou understand that security is about both breaking systems and integrating findings into operational and compliance posture.
Benefits
Comprehensive Private Medical CoverageSupport for Mental Health ExpensesLife Insurance OptionsAttractive Compensation Package
