Jobiglo

No results.

AI Agent Security Architect

replit · Foster City

Senior 🇬🇧 English
Python Go TypeScript JavaScript Model Context Protocol LangChain AutoGen CrewAI ReAct vector databases Firecracker gVisor Docker WebAssembly OWASP Top 10 for LLMs NIST AI RMF MITRE ATLAS

Job description

About the role

Replit is seeking an AI Agent Security Architect to lead the design and implementation of security controls for autonomous AI agents on its platform. You will define the security blueprint, guardrails, and sandboxing architectures that protect code execution, tool usage, and reasoning processes.

Key responsibilities

  • Define long‑term AI agent security architecture, including Model Context Protocol integrations and multi‑agent coordination.
  • Architect dynamic guardrail systems, semantic firewalls, and real‑time intent verification to prevent goal hijacking and prompt injections.
  • Design micro‑isolated execution environments (microVMs, WebAssembly, container sandboxes) for safe agent code and tool interactions.
  • Conduct threat modeling and AI red‑team exercises targeting RAG pipelines, vector stores, and tool‑calling interfaces.
  • Develop fine‑grained permission models, HITL authorization patterns, and data isolation controls for multi‑tenant workloads.
  • Maintain the AI Security Source of Truth, contribute to the Cybersecurity Risk Register, and define tamper‑evident logging and telemetry standards.

Required profile

  • 6+ years in security engineering or architecture, with at least 2 years focused on AI/ML or LLM security.
  • Proven ability to communicate complex AI risks to both technical engineers and executive stakeholders.
  • Experience authoring and evangelizing security documentation and contributing to enterprise risk registers.

Required skills

  • Python, Go, TypeScript/JavaScript
  • Agentic frameworks: Model Context Protocol, LangChain, AutoGen, CrewAI, ReAct
  • Vector database technologies and RAG pipelines
  • Sandboxing and isolation: Firecracker, gVisor, Docker, WebAssembly
  • Threat modeling and red‑team techniques for AI agents
  • Security standards: OWASP Top 10 for LLMs, NIST AI RMF, MITRE ATLAS

What we offer

  • Competitive salary and equity
  • 401(k) with 4% match (US only)
  • Health, dental, vision, and life insurance
  • Short‑term and long‑term disability
  • Paid parental, medical, and caregiver leave
  • Flexible time off and holidays
  • Commuter benefits (US office locations)
  • Monthly wellness stipend
  • Autonomous work environment and office setup reimbursement
  • Quarterly team gatherings and in‑office amenities

Questions fréquentes

Le salaire n'est pas communiqué publiquement par le recruteur. Vous pouvez postuler et négocier directement avec replit.
Cliquez sur "Postuler maintenant" en haut de la page. Vous pouvez importer votre CV en 1 clic — Jobiglo extrait automatiquement vos informations et postule pour vous.
Source : ats:ashby

Why are you reporting this job?

Thank you for your report. We will review this job.

Explore further

Salaries, guides and searches in the United States.

Apply in 30 seconds

Enter your email to apply. An account will be created automatically.

Apply now →

By continuing, you accept our terms of use.

Already have an account? Login

A question about this job?

Ask it here: you will get the full job summary by e-mail, right away.

Published 3 weeks ago

Expires 1 month from now

14 views · 0 interested

Boost your chances

Upload your CV — we will match you with relevant openings.

Analyzing your CV...

replit

Foster City