3 часа назад
Corporate Security Engineer (AI)
Мэтч & Сопровод
Для мэтча с этой вакансией нужен Plus
Описание вакансии
Текст:
TL;DR
Corporate Security Engineer (AI) (LLM/RAG security and governance): Securing AI integrations, LLM deployments, RAG pipelines, AI APIs, and automation tools across a regulated financial-services environment with an accent on threat detection, data protection, and AI governance. Focus on designing controls for prompt injection, model poisoning, data leakage, excessive agent permissions, DLP, regulatory mapping, and shadow AI monitoring.
Location: Hybrid in Warsaw, Poland; Limassol, Cyprus; or Sofia, Bulgaria
Company
is a rapidly expanding financial-services company operating at the forefront of the digital-assets movement.
What you will do
- Assess the security of LLM deployments, RAG pipelines, AI APIs, and AI-enabled automation tools, including configurations, access controls, and data flows.
- Conduct threat modelling and define secure deployment patterns for AI integrations and initiatives.
- Detect and mitigate prompt injection, jailbreaks, model poisoning, data leakage, adversarial attacks, insecure model serialisation, and excessive permissions in AI agents.
- Develop guardrails, content filters, output validation, monitoring, and DLP controls for AI channels and tools.
- Govern AI tool usage, investigate anomalous behaviour, conduct vendor due diligence, and control shadow AI across the organisation.
- Own the AI security governance framework, risk register, regulatory mapping, and audit evidence for management, auditors, and regulators.
Requirements
- 3–5+ years of cybersecurity experience with hands-on AI/ML system security or a strong AI security focus.
- Deep knowledge of AI-specific security risks, including prompt injection, model poisoning, data leakage, adversarial attacks, and excessive AI-agent permissions.
- Hands-on experience securing LLM integrations, RAG pipelines, and AI APIs.
- Experience authoring AI security policies, standards, risk-classification frameworks, and maintaining AI risk registers.
- Familiarity with the EU AI Act, NIST AI RMF, ISO/IEC 42001, GDPR, and regulated financial-services requirements.
- Python proficiency, third-party AI tool due diligence experience, and strong cross-functional communication skills.
Nice to have
- CISM, CISSP, or an equivalent certification.
- Fintech or regulated financial-services experience and multi-jurisdiction compliance exposure.
- Experience building AI-powered security automation, including autonomous agents, LLM-driven triage, and automated response workflows.
- Experience presenting AI security risk posture to leadership or board-level audiences.
Culture & Benefits
- Hybrid work environment with location-specific benefits and perks.
- Annual leave, comprehensive health insurance, and pension benefits.
- Up to 30 additional days to work remotely from anywhere in the world, subject to restrictions.
- Two additional paid volunteer days annually.
- Employee referral programme and a collaborative environment spanning risk, compliance, product, and engineering.
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 →
Похожие вакансии
4 дня назад
Senior Security Engineer, AI & Automation
1 день назад
Security & Test Engineer (AI Security)
9 часов назад
Senior Detection Engineer (AI-Augumented)
1 день назад
Security Engineer with MCP Security, AI Governance Platform (AI)
4 дня назад
Security Detection Engineer III (Cybersecurity)
21 час назад