Platform Security Engineer: Build Guardrails for Safe AI

Brain Co.; San Francisco (CA); On-site; USD 150,000 - 230,000; Full time

Job summary

Brain Co. is seeking a Platform Security Engineer to build guardrails for AI agents running on customer data. You’ll ship production code to constrain access, define data boundaries, and implement audit trails, so agents operate safely on sensitive government, healthcare, and enterprise data.

You’ll work embedded with product and agent-platform teams, writing production code rather than policy, to ensure the secure path for agent workflows and protect data integrity.

Qualifications

• 5 to 8 years as a software engineer building and shipping production systems with security, data protection, or trust & safety focus
• Strong general-purpose programming skills (Python, Go, TypeScript, or similar)
• Experience with AI agents in production, tool use, function calling, orchestration frameworks (LangChain, LangGraph)
• Data protection fundamentals: PII handling, access control, encryption, least privilege
• Designing systems with clear interfaces, sensible defaults, predictable failure modes
• Cloud experience (AWS, GCP, or Azure)
• SDLC awareness; design guardrails that don’t create friction
• Strong written English; ability to write docs/runbooks

Responsibilities

• Design and build guardrail services that mediate actions by AI agents and enforce scoped permissions
• Write production code for data access controls to keep PII and sensitive records inside approved boundaries
• Build reusable guardrail libraries and SDKs for fast adoption in new agent workflows
• Design detection and containment for failure modes, prompt injection, tool misuse, data exfiltration; build automated tests and red-team harnesses
• Instrument agents with tamper-evident audit logs and decision trails for explainability
• Partner with product, platform and ML engineering to review new agent capabilities before launch
• Own the developer experience for guardrails with clear APIs and documentation
• Define and measure guardrail effectiveness and coverage across security workflows

Skills

Software engineering

APIs design

Cloud experience

English writing

Tools

Python

Go

TypeScript

LangChain

LangGraph

Job description

Brain Co. is seeking a Platform Security Engineer to build guardrails for AI agents running on customer data. You’ll ship production code to constrain access, define data boundaries, and implement audit trails, so agents operate safely on sensitive government, healthcare, and enterprise data.

You’ll work embedded with product and agent-platform teams, writing production code rather than policy, to ensure the secure path for agent workflows and protect data integrity.