Senior LLM Release Engineer, Private Cloud Compute

Apples Private Cloud Compute team is looking for a highly technical Senior Engineer to drive the deployment of Large Language Models (LLMs) that power Apple Intelligence across hundreds of millions of iOS devices. This is a high-visibility high-impact role at the center of Apples next-generation datacenter initiatives. We are seeking a practitioner who thrives at the intersection of complex systems and high-stakes executionsomeone who wants to define how world-class distributed systems are tested validated and scaled this role your technical decisions will directly impact the user experience of a global customer base. You will be responsible for the infrastructure that ensures LLM inference is performant secure and reliable working directly on the systems that bridge the gap between cloud-scale compute and on-device intelligence.

As a Senior Engineer on the Private Cloud Compute team you will be the technical driver for the build pipelines automation infrastructure and validation frameworks that underpin Apples most complex distributed systems. This is a hands-on role where you will operate across the full stack ensuring that next-generation datacenter technology is ready to scale to a massive will be expected to provide deep technical expertise to every initiative you own from designing CI/CD systems at scale to resolving the most complex system-level issues. You will collaborate with platform and software teams to validate novel compute platforms before they reach production building the tooling and automation that allows Apple to move with speed and role requires a unique blend of release engineering excellence and LLM inference acumen. You will partner with teams across Appleincluding Foundation Models AIML and Securityto adapt and scale software on novel compute platforms. If you are a senior practitioner who thrives on solving hard problems and building systems that have never been built before this is the role for you.

Pipeline Ownership: Design and maintain the build pipeline for LLMs on Private Cloud Management: Manage model weights across OS release trains and coordinate server-side model Rollouts: Build and automate staged rollout systems across OS releases and Private Cloud Compute -Functional Execution: Partner with Foundation Models AIML Privacy and Security teams to ensure successful major Reliability: Lead incident response and postmortems for inference release issues to ensure 24/7 : Drive daily build qualification and provide critical recommendations for staging and production environments.

10 years of experience in release engineering build infrastructure and production releases for large-scale Coding Skills: Expert-level proficiency with C Swift and Python at Scale: Proven track record of designing and operating large-scale build systems with a focus on cost efficiency caching and flake -Stakes Delivery: Experience shipping software on tight non-negotiable deadlines tied to major hardware or OS in Computer Science or equivalent experience. MS or PhD is a plus.

Inference Expertise: Experience validating ML or LLM workloads running on hardware accelerators (GPUs NPUs or Apple Silicon) in cloud or datacenter -Level Systems: Experience building test infrastructure at the hardware-software boundary including firmware drivers or low-level platform Engineering: Knowledge of energy efficiency and performance profiling for high-performance computing Infrastructure: Prior experience working in private cloud hyperscale datacenter or edge compute environments.