About the role
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: Building the actual execution infrastructure for AI agents.
Responsibilities
- Implement agent runtime and orchestration components.
- Build tool-calling and execution interfaces.
- Support multi-step and long-running task execution.
- Manage task state, execution history and asynchronous workflows.
- Implement error handling, retries and recovery mechanisms.
- Integrate multiple model providers.
- Build observability and tracing for agent execution.
- Optimize latency, reliability and inference costs.
- Work with context and memory components to provide relevant information to agents.
Requirements
- Strong backend engineering experience.
- Experience with distributed systems and asynchronous workflows.
- Experience integrating LLMs into production applications.
- Strong API and service architecture knowledge.
- Experience with queues, state management and observability.
- Good understanding of tool calling and structured outputs.
Nice to have
- Production agent framework or custom agent runtime experience.
- Experience with Temporal or similar workflow orchestration systems.
- Experience with model routing and inference optimization.
- Experience with AI evaluation and tracing.