Platform Security [US]

Brain Co.
San Francisco
Workplace: HybridFull timeFunction: Solutions Engineering & Sales EngineeringExperience: 5-8 yearsSkills: ["Documentation","Runbook writing","Systems design","API design","Collaboration"]

Build and ship production “guardrail” services that keep AI agents safe when operating on sensitive customer data. Design scoped credentials, data access boundaries, tool/action validation, and tamper-evident audit trails, then package them into reusable libraries and SDKs for other engineers. Partner with product, platform, and ML teams to review new agent capabilities, add red-team testing and detection for failure modes, and measure guardrail effectiveness across security workflows.

Loading

Loading job details...

Preparing the role view and application actions.

FursaFursa
Brain Co.
Brain Co.
21 hours ago

Platform Security [US]

✓ Verified Job

Canonical indexed version, validated from employer's careers page.

Source: Company careers pageValidated by: Fursa AI
Last checked: 9 hours agoStatus: Live

Job Summary

Build and ship production “guardrail” services that keep AI agents safe when operating on sensitive customer data. Design scoped credentials, data access boundaries, tool/action validation, and tamper-evident audit trails, then package them into reusable libraries and SDKs for other engineers. Partner with product, platform, and ML teams to review new agent capabilities, add red-team testing and detection for failure modes, and measure guardrail effectiveness across security workflows.
Location: San Francisco
Workplace: Hybrid
Employment Type: Full time
Job Function: Solutions Engineering & Sales Engineering
Seniority: Mid level

Key Responsibilities

  • •Design and build guardrail services that mediate AI agent actions, scoped permissions, tool-call validation, and hard limits on what agents can read/write/send.
  • •Write production data access controls to keep customer PII and sensitive records inside approved boundaries during orchestration.
  • •Build reusable guardrail libraries and SDKs so engineers can integrate permissioning and data protection into new agent workflows.
  • •Design detection and containment for agent failure modes (prompt injection, tool misuse, data exfiltration) and build automated tests and red-team harnesses.
  • •Instrument agents with tamper-evident audit logs/decision trails and partner with product/platform/ML teams to review and launch agent capabilities safely.

Key Requirements

  • •5 to 8 years as a software engineer building and shipping production systems with meaningful security/data protection/trust & safety work.
  • •Strong programming skills in Python, Go, TypeScript, or similar, including designing services and APIs for other engineers.
  • •Experience with or strong working knowledge of AI agents in production (tool use/function calling, orchestration frameworks like LangChain/LangGraph).
  • •Solid data protection fundamentals: PII handling, access control, encryption, and least privilege (especially once an agent is in the loop).
  • •Working cloud experience with AWS, GCP, or Azure and comfort across the SDLC without adding friction.
Experience:5-8 yearsAI agentsSecurityData protectionRegulated industries
Skills:DocumentationRunbook writingSystems designAPI designCollaboration
Languages:English
Tech Stack:PythonGoTypeScriptLangChainLangGraphAWSGCPAzure

Company Brief

Brain Co.
Brain Co. builds agent-native operating systems for regulated institutions across government, health, insurance, finance, and enterprise. Its platform emphasizes secure deployment, workflow integration, and AI applications tailored to complex operational environments.
Industry: AI & Machine Learning
Growth: Growth Stage Startup
Headquarters: San Francisco, United States
Founded: 2026
WebsiteLinkedIn