6 дней назад
Sr./Staff AI Security Engineer (AI)
Мэтч & Сопровод
Для мэтча с этой вакансией нужен Plus
Описание вакансии
Текст:
TL;DR
Sr./Staff AI Security Engineer (AI): Assessing and securing LLMs, generative AI services, agentic systems, and AI data flows with an accent on threat modeling, governance, and security-by-design controls. Focus on designing mitigations for prompt injection, data leakage, model integrity, agentic behavior risks, and secure model serving across the AI development lifecycle.
Location: Taipei, Taiwan; onsite
Company
is a global cloud security company providing internet content security and threat management solutions for businesses and consumers.
What you will do
- Lead threat modeling and security risk assessments for LLMs, generative AI services, agentic and multi-agent systems, and AI data governance.
- Work with legal and compliance teams to align AI applications with internal policies, NIST AI RMF, the EU AI Act, and emerging AI regulations.
- Analyze vulnerabilities involving model integrity, training data exposure, inference endpoints, and agentic behavior.
- Design remediation plans and actionable security controls for identified AI risks.
- Implement AI security services including input/output content filters, adversarial defenses, and secure model-serving architectures.
- Embed data governance, access controls, usage policy enforcement, compliance auditing, and security-by-design practices throughout the AI development lifecycle.
Requirements
- Bachelor’s or Master’s degree in Computer Science, Cybersecurity, or a related field.
- 5+ years of software engineering experience, including at least 2 years building and deploying AI applications or AI platforms in production.
- Proficiency in Python, LLM APIs, prompt and context engineering, and AI agent or orchestration frameworks.
- Practical experience with coding assistants, agentic runtimes, and CI/CD pipeline integration.
- Familiarity with AWS, Azure, or GCP, as well as Docker and Kubernetes.
- Strong understanding of prompt injection, data leakage, model misuse, agentic behavior risks, and communicating findings to technical and non-technical stakeholders.
Nice to have
- Experience in AI/ML security, MLSecOps, or cloud-native security.
- Familiarity with AI governance and security frameworks such as ISO 42001, NIST CSF, and ISO 27001.
- Experience with shadow AI detection, non-human identity or agent identity management, and AI observability tooling.
- CISSP, CISM, CRISC, or CAISP certification.
- Experience with software supply chain security for AI models and training data.
Culture & Benefits
- Work within the Global CISO Office GRC team at a global cloud security company.
- Collaborate with product, engineering, legal, and compliance functions.
- Contribute to security practices for evolving AI systems and adoption initiatives.
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 →