Platform Security Engineer (AI)

Location: San Francisco Bay Area, hybrid

Company

hirify.global builds AI-native operating systems for large, regulated institutions, powered by agent-based workflows and the proprietary Atlas platform.

What you will do

• Design and ship guardrail services that control AI-agent permissions, tool calls, data access, and external actions.
• Build production data-access controls protecting PII and sensitive records within approved boundaries.
• Create reusable guardrail libraries, SDKs, APIs, documentation, and integration patterns for product engineers.
• Develop detection and containment for prompt injection, tool misuse, data exfiltration, and other agent-specific failures.
• Implement tamper-evident audit logs and decision trails for customer-data access.
• Partner with product, platform, and ML engineering teams to assess agent capabilities and measure guardrail effectiveness.

Requirements

• 5–8 years of experience building and shipping production software systems.
• Meaningful experience with security, data protection, or trust and safety problems.
• Strong programming skills in Python, Go, TypeScript, or a similar general-purpose language.
• Experience with AI agents in production, including tool use, function calling, and orchestration frameworks such as LangChain or LangGraph.
• Knowledge of PII handling, access control, encryption, least privilege, cloud platforms, and secure service deployment.
• Strong written English for technical documentation and runbooks.

Nice to have

• Experience building LLM or agent safety layers, including prompt-injection defenses, content filtering, or output validation.
• Experience in healthcare, government, or financial services with sensitive customer data.
• Knowledge of policy-as-code, secrets management, or software supply-chain security tools.
• Prior startup experience and comfort working autonomously in ambiguous environments.

Culture & Benefits

• Real ownership of a defined guardrail surface across the platform.
• Production-focused work with measurable customer impact.
• Close collaboration with product, platform, and ML engineering teams.
• Opportunity to shape applied AI systems for regulated institutions.