Machine Learning Systems Engineer, Siri Agent Modeling

Apple Apple · Big Tech · Cupertino, CA · Software and Services

Machine Learning Systems Engineer for Siri, focusing on optimizing model training and inference for generative AI technologies on Apple Silicon. This role involves working across the ML stack, from training to deployment, to deliver production-level code for models impacting millions of users.

What you'd actually do

  1. optimize model training and inference
  2. write production-level code to train and deploy models
  3. work with highly talented machine learning researchers and engineers
  4. work on meaningful, challenging and novel problems

Skills

Required

  • Experience in model lifecycle of training, evaluation, and deployment of models
  • Strong understanding of Machine Learning (ML) model architectures (e.g. Transformers, CNN) and ML training loop
  • Strong proficiency in Python
  • ML framework such as PyTorch
  • CUDA OOM or NCCL errors

Nice to have

  • Collaborative with experience working in large inter-teams projects
  • Expertise in ML and LLM optimization such as quantization, KV Cache, Speculative Decoding
  • Familiarity with ML training methodologies such as FSDP, DDP, and other parallelism
  • Experience in an LLM training/eval library such as HuggingFace transformers, lm evaluation harness, Megatron-LM.
  • Experience in optimizing LLM models and deploying LLM models
  • Proficiency in a compiled programming language (e.g. Swift, C/C++, Java)

What the JD emphasized

  • state-of-the-art generative AI technology
  • optimize model training and inference
  • train and deploy models
  • optimize LLM models and deploying LLM models

Other signals

  • shipping generative AI technology
  • optimize model training and inference
  • train and deploy models
  • optimize LLM models and deploying LLM models