Platform Security Engineer: Build AI Guardrails

brainco; San Francisco (CA); On-site; USD 180,000 - 240,000; Full time

Job summary

Brain Co. seeks a Platform Security Engineer to build guardrails that keep AI agents safe on real customer data. This is a builder role, writing production code to constrain access, with scoped credentials and audit trails.

You'll work with product and ML teams to design, ship secure guardrails, and ensure data protection across regulated environments in a fast-paced, production-first setting.

Qualifications

• 5 to 8 years as a software engineer with production systems.
• Strong programming in Python, Go, or TypeScript and API design experience.
• Experience with AI agents in production, tool use, and orchestration.
• Solid data protection fundamentals and least privilege concepts.
• Cloud experience across AWS, GCP or Azure and SDLC awareness.
• Clear written English and ability to document runbooks and guides.

Responsibilities

• Design and build guardrail services that constrain agent actions and data access.
• Develop production code for data protection and permissioning in agent workflows.
• Create reusable guardrail libraries and SDKs for engineers.
• Implement detection and containment for failure modes and prompt injection.
• Instrument tamper-evident audit logs and explainable access trails.
• Collaborate with product, platform and ML engineering to review capabilities.

Skills

Python

Go

TypeScript

APIs design

Security

Data protection

Cloud platforms

Tools

AWS

GCP

Azure

LangChain

Job description

Brain Co. seeks a Platform Security Engineer to build guardrails that keep AI agents safe on real customer data. This is a builder role, writing production code to constrain access, with scoped credentials and audit trails.

You'll work with product and ML teams to design, ship secure guardrails, and ensure data protection across regulated environments in a fast-paced, production-first setting.