Platform Security Engineer: Build Guardrails for AI Agents

Brain Co.; San Francisco (CA); On-site; USD 140,000 - 210,000; Full time

Job summary

Brain Co. is hiring a Platform Security Engineer to build guardrails that keep AI agents safe when handling real customer data. This is a builder role, focused on code that constrains access, actions, and exposure, with scoped credentials and audit trails in a regulated enterprise context.

You’ll work with product and platform teams to ship robust guardrails, APIs, and tests, ensuring secure, reliable agent operations across sensitive government, health, and financial service data.

Qualifications

• 5 to 8 years as a software engineer building and shipping production systems.
• Strong general-purpose programming skills in Python, Go or TypeScript and API design.

Responsibilities

• Design and build guardrail services for AI agent actions, permissions, and data boundaries.
• Write production code for data access controls that keep PII within approved boundaries.
• Develop reusable guardrail libraries and SDKs for new agent workflows.
• Design detection and containment for agent failures, prompt injection, and data exfiltration with tests.
• Instrument agents with tamper-evident audit logs and explainable decision trails.
• Collaborate with product, platform and ML teams to review new agent capabilities before launch.

Skills

Python

Go

TypeScript

APIs design

Production systems

Tools

LangChain

LangGraph

AWS

GCP

Azure

Job description

Brain Co. is hiring a Platform Security Engineer to build guardrails that keep AI agents safe when handling real customer data. This is a builder role, focused on code that constrains access, actions, and exposure, with scoped credentials and audit trails in a regulated enterprise context.

You’ll work with product and platform teams to ship robust guardrails, APIs, and tests, ensuring secure, reliable agent operations across sensitive government, health, and financial service data.