3 дня назад
AI Security Specialist
Мэтч & Сопровод
Для мэтча с этой вакансией нужен Plus
Описание вакансии
Текст:
TL;DR
AI Security Specialist (LLM Security/DevSecOps): Building and operating security controls for customer-facing AI features, internal LLM tools, agents, and AI development workflows with an accent on threat modeling, guardrails, data protection, and secure AI governance. Focus on preventing prompt injection and data leakage, defining agent permissions, integrating security checks into CI/CD, and coordinating AI-related detection and incident response.
Location: Worldwide; remote or hybrid from company offices
Company
, formerly Different Technologies, is a fintech company adopting AI across product features, developer workflows, and internal operations.
What you will do
- Own the AI Security program and maintain standards for AI development tools, LLM-powered features, and AI data handling.
- Threat-model and review customer-facing AI features, implementing defenses against prompt injection, prompt leakage, unsafe outputs, abuse, and authorization bypass.
- Secure internal LLM applications, RAG systems, agents, and developer tooling through access controls, data-scope policies, audit logging, and human-in-the-loop checkpoints.
- Evaluate AI vendors and model providers, including data residency, retention, DPAs, model provenance, and supply-chain risks.
- Partner with SOC, product, infrastructure, and ML teams on AI-related detection, incident response, remediation, and risk tracking.
- Educate engineering and product teams on AI security and translate OWASP LLM Top 10, MITRE ATLAS, and emerging research into practical guidance.
Requirements
- 2+ years of experience in DevSecOps, cloud or infrastructure security, or application security, including demonstrable hands-on AI security work.
- Working knowledge of LLM application security, including prompt injection, jailbreaks, output handling, context-based data leakage, abuse, and content safety.
- Hands-on experience with LLM APIs, agent or orchestration frameworks, tool use, RAG, and agent-permission models.
- Experience designing or evaluating AI guardrails and threat-modeling AI systems.
- Strong Python scripting skills for proofs of concept, integrations, and guardrails.
- Working knowledge of AWS security, Kubernetes security, CI/CD, container security, Terraform, OWASP Top 10, and secure coding.
Nice to have
- AI red-teaming, LLM security tooling, or AI governance framework experience.
- Fintech compliance knowledge, including PCI DSS, GDPR, or SOC 2.
- Public AI security research, CTFs, open-source contributions, talks, or technical writing.
- Service mesh experience with Istio or relevant security certifications.
Culture & Benefits
- Remote or office-based work with relocation support to hubs in Cyprus, Spain, Serbia, or Kazakhstan for employees and their families.
- Healthcare coverage, paid sick leave, and 20 days of annual vacation.
- Education budget for language lessons, professional training, and certifications.
- Wellness budget covering mental health and fitness activities.
- Collaborative environment focused on innovation, transparent feedback, and challenging established approaches in finance.
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 →