Do you feel you think differently, you are eager to break status quo, are bold and ambitious, aren’t afraid to take risks and are passionate to build the best of class technology. If yes, what better place to be at and do this than Apple? At Apple, “we think different, we push the boundaries of computing and intelligence. We build products that bring smile to people’s face”. Foundation Model Infrastructure team, within Machine Learning Platform Technologies organization is the back-bone of Apple Intelligence. It builds frameworks, services and tools that power the largest Apple foundation models on servers. Our Infrastructure powers a wide gamut of services at Apple including Apple Search, Apple Music, AppleTV, AppStore, iMessages, Photos & Camera, Spotlight, Safari, Siri and upcoming ever exciting Apple products serving millions of queries every day with incredible low latencies, drawing every ounce of compute from our hardware. As part of this group, you will get a chance to bring Intelligence to billions of users across the world. You will have an opportunity to make a difference in life of people. You will have a chance to work on optimizing billions of parameter language and vision and speech models using state of the art technologies and make it run at scale of Apple.
Description
Work along side Foundation Model Research team to optimize inference for cutting edge model architectures.
Work closely with product teams to build Production grade solutions to launch models serving millions of customers in real time.
Build tools to understand bottlenecks in Inference for different hardwares and use cases.
Mentor and guide engineers in the organization.
Minimum Qualifications
Demonstrated experience in leading and driving complex, ambiguous projects.
Experience with high throughput services particularly at supercomputing scale.
Proficient in running applications on Cloud (AWS, Azure, or equivalent) using Kubernetes and Docker.
Familiar with GPU programming concepts using CUDA and with popular machine learning frameworks like PyTorch or TensorFlow.
Preferred Qualifications
Proficient in building and maintaining systems written in modern languages (e.g. Go, Python).
Familiar with fundamental deep learning architectures such as Transformer models and encoder/decoder models.
Familiar with NVIDIA TensorRT-LLM, vLLM, DeepSpeed, NVIDIA Triton Inference Server.
Experience in writing custom CUDA kernels using CUDA or OpenAI Triton.
Eeo Content
Apple is an equal opportunity employer that is committed to inclusion and diversity. We seek to promote equal opportunity for all applicants without regard to race, color, religion, sex, sexual orientation, gender identity, national origin, disability, Veteran status, or other legally protected characteristics. Learn more about your EEO rights as an applicant.
