Real-Time AI Systems Engineer — LLM Harness & Privacy

Apple, Inc.; Cupertino (CA); On-site; USD 150,000 - 278,000; Full time

Benefits offered by this job

Medical coverage

Dental coverage

Retirement benefits

Stock programs

Tuition reimbursement

Relocation support

Job summary

Apple in Cupertino is seeking a systems engineer to advance the on-device and cloud-based harness for Siri, focusing on low-latency, privacy-preserving AI. You will work on the agent runtime, tool calls, and integration with Apple apps and services.

You will collaborate with modeling, context, and platform teams, turning designs into production features and owning components that affect hundreds of millions of users.

Qualifications

• Bachelor's degree in Computer Science or a related field.
• 2+ years of industry experience in a systems role.
• Strong programming skills in a systems language (Swift, C++, Rust, Objective-C, or Go).
• Hands-on experience building LLM-powered systems (agents, tool calls, prompt/context design).
• Experience with agent harnesses, multi-step tool-use, and latency-sensitive systems.

Responsibilities

• Build and evolve core parts of the agent runtime: planning loop, session lifecycle, concurrency, and cancellation.
• Build transcript/conversation state and the platform that defines tools and dynamic instructions for the model.
• Build the executor that dispatches tool calls into Apple apps and services and handles results/failures.
• Integrate on-device and server models, including low-latency streaming and interruption mid-response.
• Build safety, security, and privacy protections into harness components with security teams.
• Validate harness changes with evals and latency metrics and adapt to new model generations.
• Build tracing, replay, and testing tools for nondeterministic systems.

Skills

Swift

C++

Rust

Go

Objective-C

Concurrency

IPC

Performance optimization

LLM systems

Agent harnesses

Tool calling

Education

Bachelor's degree in Computer Science

Tools

Claude Code

Codex

Pi

Job description

Apple in Cupertino is seeking a systems engineer to advance the on-device and cloud-based harness for Siri, focusing on low-latency, privacy-preserving AI. You will work on the agent runtime, tool calls, and integration with Apple apps and services.

You will collaborate with modeling, context, and platform teams, turning designs into production features and owning components that affect hundreds of millions of users.