10 часов назад
AI Agent Security Architect
230 - 350$
Вакансия из Hirify Global, списка международных tech-компанийДля мэтча и отклика нужен Plus
Мэтч & Сопровод
Для мэтча с этой вакансией нужен Plus
Описание вакансии
Текст:
TL;DR
AI Agent Security Architect (AI Security): Designing runtime defense systems, guardrails, and sandboxing architectures that secure autonomous agents executing code, invoking tools, and reasoning across Replit’s platform with an accent on agentic threat modeling, least-privilege delegation, and context isolation. Focus on preventing prompt injection and goal hijacking, building micro-isolated execution environments, and translating AI security risks into enterprise-ready controls and documentation.
Location: Foster City, California, United States; hybrid
Compensation: $230–$350, plus commission offers
Company
Replit is an agentic software creation platform that enables people to build applications using natural language.
What you will do
- Define the security blueprint and architectural patterns for autonomous agent workflows, MCP integrations, multi-turn reasoning, and multi-agent coordination.
- Design runtime guardrails, semantic firewalls, intent verification filters, and policy enforcement systems.
- Build secure sandboxing and micro-isolated environments for agent code execution, shell commands, and tool interaction.
- Lead threat modeling and AI red-teaming across RAG pipelines, vector stores, context systems, and tool-calling interfaces.
- Architect fine-grained permissions, delegated access, and Human-in-the-Loop authorization for agents acting for users.
- Define secure design patterns, observability standards, risk-register contributions, audit documentation, and enterprise AI security controls.
Requirements
- 6+ years of experience in security engineering or security architecture, including 2+ years in AI/ML security, LLM application security, or agentic framework security.
- Deep knowledge of agentic architectures and protocols, including MCP, LangChain, AutoGen, CrewAI, ReAct, and vector databases.
- Hands-on experience with indirect prompt injection, goal hijacking, tool parameter tampering, data poisoning, and context contamination.
- Knowledge of OWASP Top 10 for LLMs and AI Agents, NIST AI RMF, and MITRE ATLAS.
- Proficiency in Python, Go, or TypeScript/JavaScript, with experience building security tooling or guardrails and reviewing code.
- Experience documenting security architectures, communicating AI risks to technical and executive audiences, and contributing to an enterprise Cybersecurity Risk Register.
Nice to have
- Experience with runtime sandboxing and isolation technologies such as Firecracker, gVisor, Docker, or WebAssembly.
Culture & Benefits
- Full-time employment with competitive salary and equity.
- 401(k) program with a 4% match for US employees.
- Health, dental, vision, and life insurance, plus short- and long-term disability coverage.
- Paid parental, medical, and caregiver leave, flexible time off, and holidays.
- Autonomous work environment, quarterly team gatherings, wellness stipend, and in-office setup and commuter benefits.
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 →