Applied AI Engineer, Agent Harness

What you'll do

• Develop runtime components for planning, sessions, concurrency, cancellation, conversation state, and tool execution.
• Integrate on-device and server models, including low-latency streaming and interruptions.
• Protect safety, security, and privacy; validate changes with evals and latency metrics, and build tracing, replay, and testing tools.

What they ask for

• Bachelor's degree in Computer Science or a related field.
• Strong programming skills in a systems language such as Swift, C++, Rust, Objective-C, or Go; solid foundation in concurrency, inter-process communication, and performance optimization.
• Hands-on experience building LLM-powered systems, through professional work or substantial personal projects.
• Daily use of agentic coding tools such as Claude Code, Codex, or Pi.

Nice to have

• Experience with Swift and Apple platform development, agent harnesses, model inference integration, evals, or engineering platforms and APIs.
• Familiarity with production privacy and security engineering and current agent harness research and practice.

Pay

$150,400 and $277,600 (base salary)

Tools

Swift, C++, Rust, Objective-C, Go, Claude Code, Codex, Pi

AI focus

Build the runtime harness for Siri: agent planning and tool use, context and conversation state, model integration, evals, and debugging across on-device and server models.