2 days ago
Seoul, Korea, SouthSenior
Responsibilities
- Design the overall security and privacy architecture for an AI-native phone.
- Define permission models, access boundaries, authentication, authorization, and access controls for AI agents, tools, and application integrations.
- Secure AI access to messages, contacts, calendars, notifications, camera, microphone, location, and other sensitive information.
- Implement sandboxing, isolation, audit logging, user-visible activity tracking, encryption, secure storage, retention, and deletion mechanisms.
- Identify and mitigate AI-specific risks including prompt injection, malicious applications, data exfiltration, unauthorized tool execution, and LLM data leakage.
- Review Android permission models, privileged system access, SELinux policies, Binder IPC, and system-level security boundaries.
- Conduct security assessments, threat modeling, vulnerability assessments, and penetration testing for system-level AI capabilities.
- Collaborate with Android/AOSP, Agent Runtime, Context & Memory, and Applied ML teams to build security into the architecture.
Requirements
- Strong experience in mobile security, Android security, application security, or systems security.
- Deep understanding of Android security architecture, including application sandboxing, permissions, SELinux, Binder IPC, and privileged system services.
- Experience designing authentication, authorization, and access-control systems.
- Strong understanding of encryption, secure storage, key management, and data protection.
- Experience with security threat modeling, vulnerability assessment, and penetration testing.
- Understanding of privacy-by-design principles, data minimization, and user consent.
- Ability to work across Android platform, backend, and AI agent architectures.
- Preferred experience with AOSP security customization, Android platform security, system-level applications, privileged Android services, AI agent security, prompt injection, tool-use security, LLM data leakage, mobile device security, Trusted Execution Environment, hardware-backed keystores, secure boot, privacy engineering, and permission or approval systems for autonomous agents.
Categories
About Bjak
Bjak builds an online insurance marketplace for consumers in Malaysia and Southeast Asia, enabling comparison and purchase of car, health, life, and travel policies. Its business model is aggregator-based, earning commissions and fees from insurers and partners while streamlining digital applications and renewals. Founded in 2019 and headquartered in Selangor, it is privately held and is expanding from insurance comparison into broader fintech services via a planned finance super app.