Bjak Finance/FinTech

AI Phone - AI Systems / Agent Architect

Taipei, Taiwan In person Full-time

ABOUT We are reimagining the phone. AI phones need to be proactive, intuitive, intelligent and low cost. This is a mission critical for rest of the world to adopt intelligence. There are over 5 billion people using everyday applications such as email, messaging, notes, tasks, and calendars, yet most are not AI-native. Our mission is to build proactive applications and devices that bring intelligence into daily conversations, coordination and workflows, with minimal prompting.

Focus: Agent runtime, context, memory, orchestration and overall AI system architecture. Responsibilities - Define the overall AI architecture for the phone. - Design how AI agents interact with the OS and applications. - Define agent runtime and orchestration architecture. - Design context and memory systems that allow AI to understand user activities, preferences and ongoing tasks. - Define how agents execute multi-step workflows across different applications. - Design long-running task execution, state management and recovery mechanisms. - Define model routing between on-device and cloud models. - Evaluate the feasibility of running different AI capabilities locally versus remotely. - Work with Android engineers to define the interfaces required for system-level AI execution. - Establish reliability, observability and evaluation standards.

Requirements - Strong backend and distributed systems engineering experience. - Experience building production AI agent systems or complex orchestration systems. - Strong understanding of LLMs, tool calling, structured outputs and agent execution. - Experience with stateful workflows and multi-step task execution. - Experience with context engineering, retrieval and memory systems. - Strong system design and architecture skills. - Ability to work across backend, AI and platform engineering.

Nice to have - Experience building AI assistants or agent platforms. - Experience with long-running autonomous workflows. - Experience with model routing and inference optimization. - Experience with on-device AI or hybrid local/cloud architectures. - Experience with permission-aware tool execution and agent security.

Job description provided by Bjak.
View the original posting