Software Engineer (AI Product Security)
Posted Updated
- Notion is looking for an experienced engineer who has designed and built secure software systems to help define the security foundations for our AI products
- You’ll work with product and engineering teams on agent runtimes, tool permissions, retrieval, content writes, observability, and abuse-resistant design
- You’ll turn product risks into clear architecture, reusable guardrails, automated tests, and production systems that help teams ship new features safely
- Define and build security architecture for product surfaces that operate across customer 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 reusable libraries, review patterns, test fixtures, and guardrails that prevent classes of vulnerabilities
- Build automated red-team and regression testing for risks such as prompt injection, indirect instruction following, data exfiltration, tool misuse, cross-tenant leakage, and unsafe workspace mutations
- Translate threat models for new product surfaces into concrete engineering requirements, production checks, and launch criteria
- Use production signals, incident learnings, and targeted experiments to harden Notion over time, then feed those learnings back into architecture and developer workflows
- Help define the security bar for how engineers use coding agents, MCP-enabled tools, hooks, and internal automation without introducing new risk
- You don’t need deep AI expertise for every role, but we do expect every Notino to be intellectually curious, drawn to tinkering and discovery, and excited to use AI as a real collaborator in their work
- For some roles, AI fluency is a core requirement — when that’s the case, we’ll say so explicitly in the qualifications. People who thrive here don’t treat AI as a novelty. They use it to think better, and make their work easier for others to build on
- Security architecture judgment: You can look at a complex system and reason about where the permissions, data flow, or trust boundaries are likely to get weird, and help re-design it to make them better
- Builder mindset: You’d rather leave behind a useful tool, test, library, or pattern than a task or project for someone else to pick up later
- Security product strategy: You can turn a complex security risk you see into a product design or architecture that can be built
- Secure software engineering craft: You have 8-10+ years of experience designing, building, or securing complex software systems, and you are comfortable working in production code with product and platform engineers
- We hire talented people from a wide range of backgrounds. If you’re excited about this role but don’t meet every bullet, we still encourage you to apply
- Experience building or securing products with tool use, retrieval, workflow automation, content writes, or complex permission boundaries
- Hands-on experience with prompt-injection testing, red teaming, model behavior evaluation, or abuse-resistant application design
- Experience with enterprise SaaS security models: permissions, sharing, audit logs, data residency, encryption, compliance, or customer-facing trust guarantees
- Experience building developer tooling, CI checks, coding-agent workflows, MCP integrations, or internal frameworks that shape how engineers build software
- Public security research, vulnerability writeups, conference talks, or open-source work related to product security or secure developer infrastructure