Employment Information
Summary
Role Number:200577494
Apple's Machine Learning Platform Technologies group is offering an internship on the ML Infrastructure team. Our team builds core systems that empower Apple's most advanced machine learning models. Our infrastructure supports services across Apple -- from Search and Music to Siri and Photos -- delivering millions of ultra-low latency responses every day.
Description
As an intern, you'll work on real-world projects focused on analyzing and optimizing model runtime performance and improving developer tooling. This hands-on role is a unique opportunity to dive deep into high-impact engineering. You will gain hands-on experience with large-scale ML projects, benefit from mentorship by experienced engineers, and collaborate with teams across Apple.
Minimum Qualifications
- Currently pursuing a Bachelor's degree (senior level) or Master's degree in Computer Science, Machine Learning, or a related field.
- Strong background in Machine Learning, with a focus on Deep Learning.
- Proficiency in Python or Go.
Preferred Qualifications
- Experience with NVIDIA TensorRT-LLM, vLLM, DeepSpeed, or NVIDIA Triton Server.
- Knowledge of CUDA programming and experience writing custom CUDA kernels.