ML Infrastructure Software Engineer

Summary

Posted:Apr 11, 2025

Role Number:200599493

Do you love creating elegant solutions to highly complex challenges? Do you intrinsically see the importance in every detail? As part of our Silicon Technologies group, you’ll help build AI-driven solutions that solve pressing business challenges. You’ll ensure Apple products and services can seamlessly and efficiently handle the tasks that make them beloved by millions. Joining this group means you’ll be responsible for crafting and building the technology that fuels Apple’s devices. We are looking for an individual who is passionate about joining Apple’s engineering team as an ML Infrastructure Software Engineer to enable the deployment and integration of AI models supporting our domains.

Description

In this highly visible role, your primary responsibilities will include: – Deploying, optimizing, and integrating industry-standard AI models within internal infrastructure to support silicon design workflows. – Collaborating with internal teams to evaluate model needs, define selection and benchmarking standards, and ensure our infrastructure remains state-of-the-art by tracking industry advancements. – Managing pipelines for fine-tuning and model conversion, and implementing monitoring to ensure scalable and efficient model deployment. – Contributing to compute planning and hardware decisions, including evaluating third-party silicon and supporting adoption of internal chip solutions.

Minimum Qualifications

• Experience in Python
• Experience with at least one of the following model deployment frameworks: VLLM, Triton, or TensorRT-LLM
• Experience scaling or optimizing machine learning models in production environments
• Minimum requirement of BS and 3+ years of relevant industry experience

Preferred Qualifications

• Understanding of model optimization techniques (e.g., quantization, pruning, or format conversions)
• Familiarity with containerization and orchestration tools such as Docker or Kubernetes
• Ability to evaluate model choices based on hardware efficiency and constraints
• Exposure to performance monitoring and observability systems for ML workloads
• Designed and optimized RESTful services