Full Stack AI Systems Engineer

Apple•San Diego, CA

About The Position

Apple's Stability Engineering team is seeking a seasoned engineer to join their Core team. This role focuses on building and operating platforms, services, and infrastructure that transform crash reports from Apple devices into actionable engineering insights. The position involves working with systems that already incorporate LLMs and agents into their production fabric, with responsibilities including evolving these systems, enhancing their reliability, and leveraging AI tools to amplify the team's output. The team owns the end-to-end platform for stability analysis at Apple, encompassing crash log symbolication, data aggregation and clustering pipelines, and the applications and services used by engineers across Apple to improve operating-system quality. The role requires maintaining this platform's health, expanding its capabilities, and improving the engineering team's effectiveness through proficient use of AI tools. Daily tasks include tuning evaluation infrastructure, strengthening operational controls, enhancing auditability and debug trails, and scaling workflows for stability analysts. New capabilities will be prototyped and integrated into the platform. Collaboration will occur with stability analysts, domain experts in OS reliability, and the broader team responsible for symbolication, ETL, and service infrastructure. Proficiency in using AI-assisted development tools for issue investigation, large-scale refactoring, and efficient delivery is expected. The ideal candidate possesses the rigor of a seasoned production engineer and is comfortable managing systems with LLMs and agents as core components. This role is for individuals who enjoy taking ownership of complex, operational platforms and driving continuous improvement.

Requirements

5+ years of professional software engineering experience building and operating production systems
BS in Computer Science or a related field, or equivalent practical experience
Fluent use of AI-assisted development tools (coding agents, code review assistants, etc.) to work effectively at scale
Demonstrated experience designing and scaling distributed systems (load balancing, active-active topologies, capacity planning, throughput-bound services)
Track record of maintaining and evolving production services — observability, operational controls, incident response, and steady iteration on existing systems
Strong full-stack instincts; comfortable spanning data infrastructure, backend services, and the user-facing surfaces that consume them
Proven ability to operate independently on ambiguous, open-ended problems where the right answer is not obvious

Nice To Haves

Experience operating LLM- or agent-based features in production environments over time
Experience building or maintaining evaluation harnesses, audit trails, or replay infrastructure for AI systems
Background in developer tools, observability, crash/stability analysis, or other operating-system-quality domains
Familiarity with one or more of: Ruby on Rails, Node.js/TypeScript, Python for production services
Experience working in environments with significant deferred scalability work (capacity-constrained, long-lead-time infrastructure)

Responsibilities

Keep the stability analysis platform healthy and extend its capabilities.
Make the engineering team more effective by using AI tools.
Tune evaluation infrastructure.
Tighten operational controls.
Improve auditability and debug trails.
Scale the workflows that stability analysts rely on.
Prototype and integrate new capabilities into the platform.
Partner closely with stability analysts and the broader team responsible for symbolication, ETL, and service infrastructure.
Use AI-assisted development tools fluently to investigate issues, refactor at scale, and ship more with a small team.
Take responsibility for a complex, already-running platform and make it steadily better.