3 hours ago
Base Salary
$230 - $350/yr
Responsibilities
- Define the long-term security architecture and technical patterns for autonomous agents, MCP integrations, multi-turn reasoning, and multi-agent coordination.
- Architect and deploy runtime guardrails, semantic firewalls, intent verification filters, and policy-enforcement systems.
- Design secure, short-lived, micro-isolated execution environments for agent code, shell commands, and tool use.
- Conduct agentic threat modeling and lead automated and manual AI red-team initiatives.
- Design fine-grained permissions, delegated authorization, Human-in-the-Loop controls, and least-privilege protections for agents.
- Secure vector databases, RAG pipelines, and long-term agent memories through data isolation and poisoning-prevention controls.
- Maintain authoritative AI security design patterns and SDKs for engineering teams.
- Document agentic security risks in the Cybersecurity Risk Register using relevant industry frameworks.
- Establish tamper-evident logging and telemetry standards for agent reasoning, tool execution, and context assembly.
- Translate AI security controls into enterprise audit documentation and support Sales with complex AI security inquiries.
Requirements
- 6+ years of experience in security engineering or security architecture, including at least 2+ years dedicated to AI/ML security, LLM application security, or agentic-framework security.
- Deep understanding of agentic architectures and protocols, including MCP, LangChain, AutoGen, CrewAI, and ReAct frameworks.
- Hands-on knowledge of indirect prompt injection, goal hijacking, tool parameter tampering, data poisoning, and context contamination.
- Strong experience applying OWASP Top 10 for LLMs & AI Agents, NIST AI RMF, and MITRE ATLAS.
- Proficiency in Python, Go, or TypeScript/JavaScript, with experience reviewing code and building security tooling or guardrails.
- Experience authoring, maintaining, and promoting technical security architecture documentation.
- Ability to communicate complex non-deterministic AI risks to technical engineering teams and executive stakeholders.
- Demonstrated experience contributing to an enterprise Cybersecurity Risk Register.
- Experience designing runtime sandboxing and isolation technologies such as Firecracker, gVisor, Docker, or WebAssembly is a bonus.
Benefits
- Competitive salary and equity.
- 401(k) program with a 4% match for US employees.
- Health, dental, vision, and life insurance.
- Short-term and long-term disability coverage.
- Paid parental, medical, and caregiver leave.
- Flexible Time Off and holidays.
- Commuter benefits for in-office US employees.
- Monthly wellness stipend.
- Autonomous work environment.
- In-office setup reimbursement for in-office employees.
- Quarterly team gatherings and in-office amenities.
Tech Stack
Categories
About Replit
Replit is the agentic software creation platform that enables anyone to build applications using natural language. With millions of users worldwide and over 500,000 business users, Replit is democratizing software development by removing traditional barriers to application creation.