Senior AI Security Engineer — Enterprise Guardrails

Affirm; Chicago (IL); On-site; USD 204,000 - 290,000; Full time

Benefits offered by this job

Health coverage for employee and their

Monthly tech stipends

Flexible time off

Job summary

Affim is seeking a security engineer to lead the end-to-end AI/LLM security review process, evaluating architecture, data flows, and tool configurations while embedding security throughout the development lifecycle.

You will threat model, review prompts and MCP definitions, and build guardrails with Python and IaC, collaborating with Security, Legal, Privacy, Compliance, IT, and Engineering to scale and repeat this process.

Qualifications

• 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 against OWASP Top 10 for LLM Applications.
• Proficient in building governance artifacts (acceptable use policy, data-handling standards) and evaluating vendor AI capabilities.
• Skilled in developing security tooling, guardrails, and detections with Python and IaC.

Responsibilities

• Lead and continuously improve enterprise AI security review processes for architecture, data flows, and design, embedding security into the development phase.
• Threat model AI/LLM systems and data flows, identifying risks like prompt injection, data exposure, and tool-permission abuse, driving remediation.
• Review source code, system prompts, and MCP configurations; help tool owners build security-focused test cases and red-team scenarios.
• Design and build security guardrails and tooling for AI systems, authn/authz for agent tools, data handling, logging, and policy-as-code.
• Evaluate third-party SaaS vendors for security controls and drive risk-based adoption decisions.
• Identify emerging vulnerabilities and contribute to AI-specific incident response playbooks as a senior escalation point.
• Lead cross-functional initiatives across Security, Engineering, Legal, Privacy, and Compliance; communicate with technical and executive audiences.

Skills

Security Architecture

Threat Modeling

AI/LLM Security

Python

Infrastructure as Code

Kubernetes

AWS

OAuth2/SAML

Non-human Identities IAM

Tools

CASB

IDP/Okta

Notion

Slack

Google Workspace

Jira

GitHub Copilot

Job description

Affim is seeking a security engineer to lead the end-to-end AI/LLM security review process, evaluating architecture, data flows, and tool configurations while embedding security throughout the development lifecycle.

You will threat model, review prompts and MCP definitions, and build guardrails with Python and IaC, collaborating with Security, Legal, Privacy, Compliance, IT, and Engineering to scale and repeat this process.