Apple Intelligence Cloud Performance Engineer

Join the Apple Service Engineering (ASE) team and drive innovation that matters! The ASE team builds and provides systems and infrastructure that fuel Apple's services. As part of this team, you will be responsible for building and integrating technologies that enhance people's lives. We are also tasked with enabling Apple Intelligence and Private Cloud Compute in the cloud. We are seeking a System Performance Engineer with a proven track record of developing technology that has made a significant impact.

Collaborate cross-functionally with architecture, platform design, SOC architects, and software teams to deliver exceptional end-to-end performance that delights our customers. In this role, you'll be responsible for the performance of one or more products. Specifically, you'll be tasked with ensuring the performance of Private Cloud Compute running Apple Intelligence in the cloud. This position demands technical expertise and depth to work on various elements of the stack, from SOC to the platform along with the software stack. You'll collaborate with architecture and software teams to define the product and set its power and performance targets and develop automation and infrastructure tools to evaluate the performance of our Apple Intelligence products. Strong problem-solving skills and effective communication are crucial for success in this role.

3+ years of experience as a Performance Engineer

Strong experience in data and AI-related fields such as software architecture or AI engineering, software development, data science, data analysis, or data lead roles, with experience across both traditional ML systems and GenAI LLMs.

In-depth professional experience with cloud operations

Strong understanding of hardware components and hardware/software interaction

Proven understanding of network technologies, protocols and procedures for iOS and macOS

Proven track record to own a complete functional area of an application or product

Able to work independently and should be dedicated

Excellent communication & interpersonal skills

Comfortable with troubleshooting/debugging/reproducing issues

Scripting and programming skills in C/C++, Python, Swift, SQL, Shell

M.S., or Ph.D. in Computer Engineering, Electrical Engineering, Computer Science

Previous experience in Performance modeling and Debugging of Transformer models, LLM inference and training.

Ability to implement and coordinate telemetry using monitoring and observability tools such as Splunk, Grafana, and Prometheus

Proficiency in SQL and experience with at least one major data analytics platform, such as Hadoop, Spark, or Snowflake.