Senior Software Engineer - Siri Agentic Evaluation Platform

Siri is the world’s most popular intelligent assistant. Available across iPhone, iPad, Mac, Apple Watch, AirPods, HomePod, Apple TV, CarPlay and Vision Pro, Siri helps hundreds of millions of people get things done - just by asking!

The Siri Agentic Evaluation team are responsible for building software platforms and tools that define, measure and report Siri quality and effectiveness. In modern software development, the hardest problem is increasingly not writing code but evaluating the quality of the product. We apply agentic technology to give rich, comprehensive and reliable feedback signals that are at the heart of the development process. These feedback signals are applied at all stages of the software lifecycle, from coding to qualifying new features for release.

Imagine what you could do here. With your passion and dedication to revolutionising the way people and machines interact, there's no telling what you could accomplish.

Description

We're seeking a Senior Software Engineer to build the platforms and agents that teams across Apple rely on to understand, improve and ship the next generation of Siri. Your work will directly inform whether a Siri feature is ready to reach customers.

Minimum Qualifications

Proven professional software engineering experience. Proficiency in Python or Swift is desirable.

Heavy day-to-day use of AI coding tools in your own development workflow.

Hands-on experience building LLM-powered agents or agentic workflows (tool use, multi-step planning, orchestration) and deploying them in real-world applications.

An eye for good architecture and a proven track record of designing and owning complex systems end to end across multiple teams.

Dedication to high-quality, well-tested code and great user experiences.

Preferred Qualifications

Excellent problem-solving, critical-thinking and communication skills.

You thrive when collaborating with peers on multi-faceted projects.