Lead AI Security Engineer - Enterprise Guardrails

Affirm, Inc.; London; Remote; CAD 181.000 - 241.000; Vollzeit

Benefits dieser Stelle

Health coverage for you and dependents

Tech stipends for your setup

Flexible time off

Employee stock purchase plan

Zusammenfassung

affirm is seeking a seasoned security engineer to own the enterprise AI security review process for AI/LLM systems, evaluating architecture, data flows, and tool configurations. You will embed security requirements into design and partner across security, legal, privacy, compliance, IT, and engineering.

You will model risks, mitigate vulnerabilities, review third-party SaaS capabilities, build guardrails with Python and IaC, and help scale repeatable security controls.

Qualifikationen

• Seasoned security engineer with hands-on experience designing, evaluating, and maintaining security architecture for AI/LLM-based systems.
• Experience threat modeling and reviewing AI/LLM apps and securing agentic systems and tool-calling frameworks.
• Knowledge of governance artifacts and evaluating SaaS capabilities for vendor reviews.
• Familiarity with enterprise tools for AI visibility and control and with corporate AI adoption platforms.

Aufgaben

• Lead and continuously improve affirm's enterprise AI security review process evaluating architecture, data flows, permissions, and design of internal AI tools, agentic/MCP-based systems, and AI features — and embed security requirements into the design phase.
• Threat model AI/LLM-based systems and their data flows for risks such as prompt injection, insecure output handling, excessive agency, tool-permission abuse, data poisoning, and sensitive-data exposure, and drive remediation.
• Review source code, system prompts, agent configurations, and tool/permission manifests (e.g., MCP definitions), and help tool owners build security-focused test cases and red-team/eval scenarios to verify requirements before launch.
• Design and build security guardrails and tooling for AI systems permission boundaries, authn/authz for agentic tools and MCP servers, data-handling controls, logging/monitoring, and policy-as-code (Python, IaC) — to enforce and automate AI security.
• Evaluate the AI capabilities of third‑party SaaS vendors (e.g., Notion, Slack, Google Workspace) as part of vendor and SaaS security reviews and drive risk‑based adoption decisions.
• Identify emerging classes of AI/agentic security vulnerabilities, develop mitigations before they become incidents, and contribute to AI‑specific incident response playbooks as a senior escalation point.
• Lead cross‑functional AI security initiatives to closure, advise technical and executive stakeholders as an internal point of expertise.

Kenntnisse

Security architecture

Threat modeling

AI/LLM security

Python

IaC

Kubernetes

Tools

CASB

Okta

OAuth2

SAML

Terraform

Jobbeschreibung

affirm is seeking a seasoned security engineer to own the enterprise AI security review process for AI/LLM systems, evaluating architecture, data flows, and tool configurations. You will embed security requirements into design and partner across security, legal, privacy, compliance, IT, and engineering.

You will model risks, mitigate vulnerabilities, review third-party SaaS capabilities, build guardrails with Python and IaC, and help scale repeatable security controls.