On-Device ML Quality Infrastructure Engineer

Summary

The On-Device Machine Learning team at Apple is responsible for enabling the Research to Production lifecycle of cutting edge machine learning models that power magical user experiences on Apple’s hardware and software platforms. Apple is the best place to do on-device machine learning, and this team sits at the heart of that discipline, interfacing with research, SW engineering, HW engineering, and products. The team builds critical infrastructure that begins with onboarding the latest machine learning architectures to embedded devices, optimization toolkits to optimize these models to better suit the target devices, machine learning compilers and runtimes to execute these models as efficiently as possible, and the benchmarking, analysis and debugging toolchain needed to improve on new model iterations. This infrastructure underpins most of Apple’s critical machine learning workflows across Camera, Siri, Health, Vision, etc., and as such is an integral part of Apple Intelligence. Our group is looking for an On-Device ML Quality Infrastructure Engineer. The role involves building and maintaining the infrastructure used to connect, validate, and benchmark the components of the On-Device Machine Learning stack.

Minimum Qualifications

Bachelors in Computer Science or relevant disciplines. Build systems (CMake, Bazel) and CI/CD experience Strong programming and software design skills in Python. In depth knowledge of quality practices and fundamentals, including test planning, automation, and performance evaluation. Excellent collaboration and communication skills.

Preferred Qualifications

Masters in Computer Science or relevant disciplines. Experience with any ML authoring framework (PyTorch, TensorFlow, JAX, etc.). Experience with standard ML architectures such as Transformers, CNNs or Stable Diffusion a strong plus. Experience with fuzz testing tools or methodologies Experience with performance profiling and analysis tools Familiarity with GenAI tooling for developer productivity or test generation.

Description

We are building the first end-to-end developer experience for ML development that, by taking advantage of Apple's vertical integration, allows developers to iterate on model authoring, optimization, transformation, execution, debugging, profiling, and analysis. As an engineer in this role, you will build and maintain the infrastructure that keeps every component of our ML stack robust and testable, and that lets our engineers move fast without breaking things. This means owning build and CI systems, developing automation frameworks, and ensuring high-quality, low-friction workflows from commit to validation. Beyond pure infrastructure, this role contributes directly to quality: writing and expanding test suites, developing robustness tests (such as fuzz testing), running performance benchmarks, and tracking regressions across the stack. You will also collaborate with Apple's broader CI and infrastructure teams to improve validation speed and scale. This is a great role for an engineer who cares deeply about software quality and wants to work at the intersection of systems infrastructure and cutting-edge ML.

Responsibilities

Design, build, and maintain build systems and CI/CD pipelines for the On-Device ML stack. Develop and maintain automation frameworks for functional, regression, and integration testing. Contribute to robustness and reliability initiatives, including fuzz testing of stack components such as parsers, compilers, and runtimes. Track and investigate performance regressions; work with engineering teams to resolve them. Identify gaps in testing coverage and tooling; drive improvements proactively. Develop and maintain tooling to help engineers diagnose, debug, and fix issues across the ML stack. Collaborate with Apple's CI and infrastructure teams to scale and accelerate validation workflows. Work cross-functionally with ML, compiler, and hardware teams to ensure infrastructure meets their needs.