Senior ML Engineer, Foundation Models Inference (Cloud OS)

Apple, Inc.; Paris; Presencial; EUR 130.000 - 190.000; Tempo integral

Resumo da vaga

Apple in Paris is seeking a Sr. Machine Learning Engineer focused on foundation models inference within Cloud OS & Inference. You will bridge research and production, optimize inference across language, vision, and speech, and shape the technical direction.

You'll own high-throughput, low-latency serving at planetary scale, mentor engineers, and collaborate with Foundation Model Research and security teams to deliver trusted, private AI workloads.

Qualificações

• Experience leading complex ML projects end to end.
• Proficiency in PyTorch or JAX and inference frameworks.
• Experience deploying models on cloud platforms with containerization.
• Strong knowledge of Transformers and multimodal architectures.
• Proven ability to ship production-grade inference systems.

Responsabilidades

• Optimise inference for latest model architectures across language, vision and speech.
• Design and ship production-grade inference systems serving millions of users.
• Build profiling tools to identify and fix performance bottlenecks.
• Drive high-throughput, low-latency serving at scale and mentor engineers.
• Collaborate with Research and security teams on privacy and trust.

Conhecimentos

PyTorch or JAX

Python / Rust / Go

Cloud platforms (AWS, GCP)

Kubernetes & Docker

Inference frameworks

Lead ML projects

Transformers / multimodal

Formação

MS in CS / ML / AI or related field

Ferramentas

Kubernetes

Docker

TensorRT-LLM

vLLM

SGLang

TGI

Nvidia Triton Server

Descrição da vaga

Apple in Paris is seeking a Sr. Machine Learning Engineer focused on foundation models inference within Cloud OS & Inference. You will bridge research and production, optimize inference across language, vision, and speech, and shape the technical direction.

You'll own high-throughput, low-latency serving at planetary scale, mentor engineers, and collaborate with Foundation Model Research and security teams to deliver trusted, private AI workloads.