Platform Security

Global Brain Corporation

. Design and build guardrail services mediating AI-agent actions, including scoped permissions, tool-call validation, and limits on reading, writing, or sending data .

Posted 9/22/2026full-timeCalifornia • United StatesMid-LevelSeniorWebsite

Core Competencies

Role fit

Core Competencies

Use this summary to align your resume positioning with the role.

Demonstrates expertise in designing and building secure guardrail services for AI agents, with a strong focus on data protection, access control, and system design. Proficient in programming languages such as Python and Go, with experience in cloud environments and a solid understanding of PII handling and security best practices.

Highest-signal resume keywords

Python ProgrammingData ProtectionAI Agent DevelopmentAWS Cloud ExperienceAccess Control

ATS Keywords

Tailor your resume

Applicant Tracking System Keywords

Tip: use these terms in your resume and cover letter to boost ATS matches.

Hard Skills

Go ProgrammingTypeScript ProgrammingProduction Systems DevelopmentSecurity EngineeringData Access ControlPrompt Injection DefenseContent FilteringOutput ValidationGuardrail Library DevelopmentAutomated Testing

Soft Skills

Strong Written EnglishDocumentation SkillsCollaboration

Tools & Technologies

LangChainLangGraphAWSGCPAzure

Industry Keywords

PII HandlingLeast PrivilegeRegulated IndustriesPolicy-as-CodeSecrets Management

Tech Stack

Tools & technologies

AWSAzureCloudGoogle Cloud PlatformPythonSDLCTypeScriptGo

About the role

Key responsibilities & impact

Design and build guardrail services mediating AI-agent actions, including scoped permissions, tool-call validation, and limits on reading, writing, or sending data
Write production data-access-control code protecting customer PII and sensitive records
Build reusable guardrail libraries and SDKs for agent workflows
Design detection and containment for prompt injection, tool misuse, and data exfiltration attempts
Build automated tests and red-team harnesses before production
Instrument agents with tamper-evident audit logs and decision trails
Partner with product, platform, and ML engineering teams to review agent capabilities and identify missing guardrails
Own guardrail developer experience through APIs, documentation, and low-friction integrations
Define and measure guardrail effectiveness, workflow coverage, false-positive/negative rates, and mean time to detect and contain

Requirements

What you’ll need

5 to 8 years as a software engineer building and shipping production systems, with meaningful time spent on security, data protection, or trust & safety problems
Strong general-purpose programming skills in Python, Go, TypeScript, or similar
Experience with or strong working knowledge of AI agents in production, tool use, function calling, and orchestration frameworks such as LangChain or LangGraph
Solid grasp of PII handling, access control, encryption, and least privilege
Experience designing systems used by other engineers, including clear interfaces, sensible defaults, and predictable failure modes
Working cloud experience with AWS, GCP, or Azure sufficient to build and deploy services securely
Comfortable across the SDLC and able to design guardrails that do not create friction
Strong written English; able to write documentation and runbooks
Direct experience building LLM/agent guardrails, prompt injection defenses, content filtering, or output validation (nice to have)
Background in regulated industries handling sensitive customer data (nice to have)
Familiarity with policy-as-code, secrets management, or software supply-chain security tooling (nice to have)
Prior startup experience and comfort with ambiguity and autonomous work (nice to have)