Adversarial Machine Learning Engineer

The OpportunityWe are building a dedicated AI Red Team to rigorously test and harden enterprise-scale AI products.We are looking for an adversarial machine learning specialist who thinks like an attacker.This role focuses on identifying vulnerabilities in LLM-driven systems, breaking model guardrails, exploiting data pathways, and stress-testing AI deployments before they reach enterprise customers.This is a hands-on technical role at the core of AI security.What You'll DoConduct adversarial testing across LLM and AI-based systemsExecute real-world attack simulations, including:Prompt injectionJailbreaking and guardrail bypassData exfiltration attemptsModel inversion and evasion techniquesRAG manipulationDevelop scripts and tooling to automate attack scenariosAnalyse model behaviour under adversarial pressureIdentify systemic vulnerabilities in:APIsEmbedding pipelinesVector databasesFine-tuned model implementationsCollaborate with engineering teams to validate remediationDocument findings clearly and conciselyYou will help ensure AI systems are resilient before they are deployed at scale.RequirementsWhat We're Looking ForCore Technical SkillsStrong experience in adversarial ML or AI security researchExperience working with LLM-based systems (OpenAI, Anthropic, open-source models, etc.)Deep understanding of:Prompt injection techniquesModel jailbreak methodologiesAI system exploitation vectorsStrong Python skillsExperience building custom attack tooling or experimentation frameworksAI Systems KnowledgeFamiliarity with:RAG architecturesVector databasesModel fine-tuning workflowsAPI-based model deploymentsUnderstanding of model safety mechanisms and guardrailsNice to HaveBackground in cybersecurity or penetration testingFamiliarity with OWASP LLM Top 10Experience working in enterprise environmentsWho You AreCurious and relentlessComfortable thinking like an attackerCreative in finding non-obvious vulnerabilitiesDetail-oriented but fast-movingComfortable operating in ambiguityIndependent but collaborativeYou don't just run test cases — you design new ones.BenefitsComprehensive Private Medical CoverageSupport for Mental Health ExpensesLife Insurance OptionsAttractive Compensation Package