AI Security Engineer: Build Secure AI Platforms

Intermedia Lab; San Francisco (CA); On-site; USD 270,000 - 340,000; Full time

Job summary

Notion is seeking an experienced security engineer to define the security foundations for our AI products. You’ll collaborate with product and engineering teams on agent runtimes, tool permissions, retrieval, content writes, observability, and guardrails to ship features safely.

This SF-based role is anchored to in-person collaboration on Anchor Days and requires 8-10+ years in secure software design, with a track record of building scalable security architectures for complex systems.

Qualifications

• Secure software engineering craft: 8-10+ years of experience designing, building, or securing complex software systems.
• Security architecture judgment: Reason about permissions, data flow, trust boundaries, and re-design for safety.
• Security product strategy: Turn risks into actionable design or architecture.
• Builder mindset: Prefer creating reusable tools, tests, and patterns over one-off tasks.

Responsibilities

• Define and build security architecture for product surfaces across workspace content, including tool execution, content writes, retrieval, permission checks, provenance, and auditability.
• Make the secure path the easy path for product teams by shipping libraries, review patterns, test fixtures, and guardrails.
• Build automated red-team and regression tests for risks like prompt injection, data exfiltration, and cross-tenant leakage.
• Translate threat models into concrete engineering requirements, production checks, and launch criteria.
• Use production signals and incident learnings to harden Notion over time and feed learnings back into architecture.
• Help define the security bar for coding agents and internal automation without introducing new risk.

Skills

Secure software engineering craft

Security architecture judgment

Security product strategy

Builder mindset

Job description

Notion is seeking an experienced security engineer to define the security foundations for our AI products. You’ll collaborate with product and engineering teams on agent runtimes, tool permissions, retrieval, content writes, observability, and guardrails to ship features safely.

This SF-based role is anchored to in-person collaboration on Anchor Days and requires 8-10+ years in secure software design, with a track record of building scalable security architectures for complex systems.