AI Software Engineer, App Intelligence

Join the App Intelligence team and help redefine what a deeply personal and integrated assistant can be. As part of the Siri organization, you will help shape one of the world's most widely used AI assistants, powered by our next generation of Apple Intelligence — with capabilities like personal context understanding and on-screen awareness, built with privacy from the ground up.

We are engineers, scientists, and problem solvers working to bring smarter, faster, and more natural interactions to millions of users worldwide. As a Software Engineer on our team, you will build the on-device runtime foundation that powers Siri, enabling seamless, intelligent, and secure experiences with direct, meaningful impact across iOS, iPadOS, macOS, watchOS, and visionOS.

Description

App Intelligence is the on-device system that turns app capabilities into things a user can simply ask for — and makes the assistant reliable enough to be trusted with them. We partner closely with the team that builds Siri's planning and execution engine, and we own the app side of that partnership: what apps can offer, how they express it, and whether the resulting experience is good enough to trust. As a platform engineer, you will build the on-device software this depends on and make the resulting experiences reliable and fast. This is early work. How apps should best expose themselves to an assistant is still an open question — you will help answer it by designing the interfaces, proving them out with real app partners, and iterating as we learn. Expect real ambiguity, and expect to form your own view of the right architecture and defend it with working software and measured results.

Responsibilities

Design, develop, and maintain the robust on-device runtime platform that enables end-to-end Siri experiences. Implement code that is well-designed, scalable, maintainable, highly testable, easy to debug, and highly performant, ensuring best practices in engineering. Contribute to and help shape key architecture decisions that enable the product to scale. Debug, profile, and optimize system performance to ensure high-quality, responsive interactions, holding on-device latency, memory, and power budgets. Diagnose failures in end-to-end Siri experiences, and turn them into measurable quality and reliability improvements in the platform. Contribute to the shared evaluation and telemetry loop that proves whether a platform change improved user outcomes. Design and evolve the interfaces between the runtime and the model — tool and function-calling schemas, context construction, and validation of model output — so that what the planner decides is executed reliably.

Minimum qualifications

BS or MS in Computer Science or equivalent practical experience, with 5+ years developing and shipping production software. Strong proficiency in C++, Swift, or Objective-C, with a solid understanding of object-oriented programming and software design principles. Strong understanding of OS internals, concurrency, multithreading, and memory management. Strong familiarity with Large Language Models (LLMs) and AI assistants, with fluency in agentic coding tools such as Claude Code, and good judgment about where to apply them and how to verify what they produce. Experience with system performance analysis and optimization techniques. Ability to work independently, solve complex problems, and learn new technologies quickly. Excellent communication skills, with experience collaborating across different technical teams and driving alignment on shared API surfaces.

Preferred qualifications

Proficiency with Swift and Xcode, with experience building applications for Apple platforms. Experience designing and developing systems that are efficient in resource-constrained environments — latency, memory, and power budgets on device. Experience working on AI software runtimes or agent orchestration frameworks, or on voice assistants / conversational AI systems leveraging LLMs. Experience building software features driven by LLMs, including designing tool and function-calling interfaces, constructing context, and validating model output. Experience with API design or framework development, including key software components and APIs used cross-functionally across different applications and platforms, and versioning and compatibility of interfaces that shipped clients depend on. Experience with evaluation or telemetry infrastructure that measures the end-to-end quality of LLM-driven features (e.g., Python, SQL, dashboards). Experience leading the design of complex features or driving architectural decisions across teams (for candidates at the more senior end of the range).