Machine Learning Inference Performance Engineer

At Apple, we're on the cutting edge of delivering transformative experiences through Artificial Intelligence. If you're passionate about pushing the boundaries of AI and hardware optimization, we want you to join our team. As a Senior Machine Learning Performance Engineer, you will help push the boundaries of on-device generative AI performance and efficiency, designing and implementing novel techniques to optimize large-scale machine learning workloads on the ANE(Apple Neural Engine). You will work at the intersection of machine learning, systems, and hardware architecture, shaping how next-generation AI models run across millions of Apple devices.

This is a unique opportunity to contribute to technologies that directly impact the daily experience of Apple customers worldwide.

Description

In this role, you will play a critical part in enabling state-of-the-art machine learning workloads on Apple silicon. You will collaborate closely with model developers, machine learning researchers, compiler engineers, and hardware architects to deliver highly optimized inference performance.

In this role, you will:

Develop novel ML inference optimization strategies to improve performance and power efficiency on the ANE.

Analyze and identify performance bottlenecks across the full stack, including model architecture, compiler, runtime, and hardware.

Partner with Apple AI/ML, software, and silicon teams to co-design next-generation ML models and inference techniques optimized for ANE.

Build and maintain performance profiling tools, benchmarking frameworks, and analysis infrastructure

* Drive performance characterization, modeling, and optimization for large-scale ML workloads such as LLMs, diffusion models, and computer vision models","responsibilities":"Strong understanding of machine learning inference workloads, including LLMs, diffusion models, or computer vision models

Deep knowledge of computer architecture, including memory hierarchy, parallelism, dataflow, and SIMD/vector processing

Hands-on experience optimizing machine learning inference on hardware accelerators (GPU, TPU, NPU, etc.)

Experience analyzing system-level performance and identifying optimization opportunities across software and hardware stacks

Strong programming skills in Python and C/C++

Preferred Qualifications

MS or PhD in Computer Science, Machine Learning, Computer Architecture, or a related field

Experience with ML system optimization, performance modeling, or architecture evaluation

Experience developing profiling tools, benchmarking frameworks, or performance analysis tools

Familiarity with hardware accelerators or ML compiler stacks

Experience with large-scale ML workloads such as transformers, diffusion models, or mixture-of-experts architectures

Strong analytical skills with the ability to analyze large datasets and communicate insights clearly

Excellent written and verbal communication skills

Minimum Qualifications