Senior AI Security Engineer — Enterprise Guardrails & Risk

Affirm; Baltimore (MD); On-site; USD 204,000 - 290,000; Full time

Benefits offered by this job

Health coverage 100% for you and your…

Monthly tech stipends and wellness

Flexible time off and holidays

ESPP – stock purchase plan

Job summary

Affim is seeking a seasoned security engineer to design, evaluate, and maintain security architecture for AI/LLM systems. You will lead enterprise AI security reviews, embed security into design, and collaborate across Security, Legal, Privacy, Compliance, IT, and Engineering.

The role requires threat modeling, governance artifacts, and hands-on tooling with Python, Terraform, Kubernetes, and AWS. Remote-first with flexible work arrangements and competitive pay.

Qualifications

• You are a seasoned security engineer with hands-on experience designing, evaluating, and maintaining security architecture for AI/LLM-based systems, plus deep expertise in enterprise security systems, processes, and controls.
• You have practical experience threat modeling and reviewing AI/LLM applications (e.g., against the OWASP Top 10 for LLM Applications) and securing agentic systems and tool-calling frameworks — MCP servers/clients, tool-permission models, and agent-to-tool trust boundaries.
• You have built AI governance artifacts (acceptable use policy, data-handling standards, vendor/model risk assessments) and evaluated AI capabilities within SaaS platforms (e.g., Notion AI, Slack AI, Google Workspace AI, GitHub Copilot) as part of vendor reviews.
• You have experience with enterprise tools for AI visibility and control (e.g., CASB, IDP/Okta) and familiarity with the corporate systems where AI is adopted (OpenAI, Anthropic, GitHub, Google Workspace, Slack, Notion, Jira).
• You can build security tooling, guardrails, and detections with Python or similar, and deploy cloud services and policy-as-code using Infrastructure as Code (Terraform or similar); familiarity with Kubernetes and AWS.
• You understand how LLMs and agentic systems are built (RAG, embeddings, fine-tuning, tool use) and authn/authz models (OAuth2, SAML, service-account/non-human identities) for agentic and machine-to-machine access, with strong application-architecture and threat-modeling fundamentals.
• You can lead cross-functional initiatives across Security, Engineering, Legal, Privacy, and Compliance and drive them to closure, and communicate effectively with technical and executive audiences. Experience in regulated environments (SOC 2, PCI DSS) and applying IAM to non-human/agent identities is a plus.

Responsibilities

• You will lead and continuously improve Affim's enterprise AI security review process evaluating the 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.
• You will 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.
• You will 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.
• You will 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.
• You will 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.
• You will 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.
• You will lead cross-functional AI security initiatives to closure, advise technical and executive stakeholders as an internal point of expertise, and stay current on the AI security landscape (OWASP LLM Top 10, MITRE ATLAS) to translate new research into practical controls.

Skills

Security architecture

Threat modeling

AI security

MCP servers/clients

Tool-calling frameworks

Python

IaC / Terraform

Kubernetes

AWS

OAuth2

SAML

Non-human IAM

Tools

Terraform

Kubernetes

AWS

Okta

Job description

Affim is seeking a seasoned security engineer to design, evaluate, and maintain security architecture for AI/LLM systems. You will lead enterprise AI security reviews, embed security into design, and collaborate across Security, Legal, Privacy, Compliance, IT, and Engineering.

The role requires threat modeling, governance artifacts, and hands-on tooling with Python, Terraform, Kubernetes, and AWS. Remote-first with flexible work arrangements and competitive pay.