Senior AI Systems Engineer - Real-Time LLM Harness

Apple Inc.; Cupertino (CA); On-site; USD 150,000 - 225,000; Full time

Benefits offered by this job

Apple Benefits

Employee stock programs

Relocation assistance

Tuition reimbursement

Discounted products and services

Job summary

Apple Inc. in Cupertino, CA is seeking a systems engineer to advance the harness for an on-device and private cloud compute setup powering a deeply personal voice assistant.

This role focuses on building the agent runtime, handling streaming, tool calls, and reliable execution within tight latency and power constraints across Apple devices. You will collaborate with modeling, tools, and context teams, and contribute from design through production, growing ownership over time as models evolve.

Qualifications

• Bachelor's degree in Computer Science or related field with 2+ years of industry experience.
• Strong programming skills in a systems language (Swift, C++, Rust, Objective-C, or Go).
• Solid foundation in concurrency, inter-process communication, and performance optimization.
• Hands-on experience building LLM-powered systems and tool calling.
• Experience using agentic coding tools and understanding harness success factors.
• Clear communication and ability to solve ambiguous problems.

Responsibilities

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

Skills

Swift

C++

Rust

Objective-C

Go

Concurrency

LLM-powered systems

Agent harnesses

Communication

Education

Bachelor's degree in Computer Science or related field

Tools

Claude Code

Codex

Pi

Job description

Apple Inc. in Cupertino, CA is seeking a systems engineer to advance the harness for an on-device and private cloud compute setup powering a deeply personal voice assistant.

This role focuses on building the agent runtime, handling streaming, tool calls, and reliable execution within tight latency and power constraints across Apple devices. You will collaborate with modeling, tools, and context teams, and contribute from design through production, growing ownership over time as models evolve.