Вакансия из Hirify Global, списка международных tech-компаний Для мэтча и отклика нужен Plus
Пожаловаться
Зарплата и рынок
ЗП не указанаразвернуть
На похожих ролях по рынку
$109к$160кмедиана$181к
49 в выборке
На СНГ рынке: $4.1к/мес ($3.2к - $5к)
75
Хорошая вакансия
развернуть
Роль четко определена с акцентом на передовую безопасность ИИ, но компания является аутсорсинговой, что может подразумевать менее благоприятный баланс между работой и личной жизнью.
Аутсорсинговая компания
Четкое определение роли
Гибридный формат работы
Возможности обучения
Мэтч & Сопровод
Для мэтча с этой вакансией нужен Plus
Подключить Plus
Описание вакансии
Текст:
Hirify AI/Оригинал
TL;DR
AI Security Engineer (Agentic Systems) (AI security/agentic systems): Designing and running adversarial tests for AI agents and agentic workflows with an accent on prompt injection, tool misuse, hallucination measurement, and governance. Focus on building repeatable account-wide testing strategies, mapping controls to OWASP, NIST, and MITRE ATLAS, and training security engineers to operate the practice.
Location: London, with genuine hybrid working
Company
hirify.global is an engineering consultancy focused on Quality Engineering, Cloud Platforms, Developer Experience, AI, security, and scalable systems.
What you will do
Design and run red-team exercises against AI agents and agentic workflows, testing prompt injection, jailbreaking, tool misuse, agent hijacking, memory poisoning, and privilege escalation.
Build repeatable evaluation methods for non-deterministic systems and measure, report, and mitigate hallucinations in agent and LLM outputs.
Own account-wide agentic AI risk identification, governance, testing strategy, and tooling recommendations.
Map risks and controls to OWASP agent risk categories, the OWASP Top 10 for LLM Applications, NIST AI RMF, and MITRE ATLAS.
Define controls for internal and client-facing agent behaviour, including output review, sanitisation, release gating, rollback, and incident response.
Advise delivery teams, represent agentic security posture to stakeholders and clients, and train security engineers to implement and automate the practice.
Requirements
Hands-on experience red-teaming or adversarially testing LLM or agentic AI systems.
Practical understanding of non-deterministic testing and detecting, quantifying, and mitigating hallucinations.
Working knowledge of agentic AI risk frameworks, OWASP LLM risks, MITRE ATLAS, and AI governance frameworks such as NIST AI RMF.
Experience with threat modelling, security reviews, and developing strategies that generalise across accounts and applications.
Strong communication skills for explaining agentic AI risks to technical and non-technical stakeholders.
Ability to implement tests directly before mentoring and training other security engineers.
Nice to have
Experience with agent-hijacking or agent-specific evaluation tooling.
Awareness of AI regulation, including EU AI Act adversarial and robustness-testing requirements.
Experience with multi-agent or agent-mesh systems and inter-agent trust and authentication.
Cloud security experience, preferably Azure, plus Terraform and CI/CD.
Experience in a regulated sector such as financial services.
Culture & Benefits
Genuine hybrid working, home office budget, flexible time off, and an open feedback culture.
Profit share, competitive salary benchmarking, private healthcare, and employee assistance covering counselling, mental health, and financial wellbeing.
Inclusive and collaborative communities, including interest-based groups, Women in Tech, monthly socials, and cross-regional events.
Learning budgets, Udemy access, career framework, internal mobility, and thought leadership opportunities.
Family-friendly working environment with flexibility and support for accessibility needs.
Будьте осторожны
Если работодатель просит войти в их систему, используя iCloud/Google, прислать код/пароль, запустить код/ПО, не делайте этого. Это мошенники. Обязательно жмите «Пожаловаться» или пишите в поддержку. Подробнее в гайде →