Senior ML Engineer: Foundation Model Inference at Scale

Apple; Paris; On-site; EUR 120,000 - 180,000; Full time

Job summary

Apple is seeking a senior ML inference architect to join the Foundation Model Inference team in Paris. You will work at the intersection of research and production, delivering scalable, secure inference systems for billions of interactions across Apple services.

You will partner with research and external partners to bring cutting-edge architectures to planetary-scale deployment, shaping the technical direction and mentoring engineers while ensuring privacy and performance at scale.

Qualifications

• Experience leading complex ambiguous Machine learning projects end to end.
• Proficiency in PyTorch or JAX.
• Experience working with Inference frameworks.
• Experience programming in Python, Go or Rust.
• Proficiency deploying applications on cloud platforms using Kubernetes and Docker.

Responsibilities

• Partner with the Foundation Model Research team and external partners to optimise inference for the latest model architectures across language, vision, and speech.
• Design and ship production-grade inference systems serving millions of customers in real time.
• Build profiling tools and simulators to identify and resolve performance bottlenecks across hardware configurations.
• Drive technical decisions on high-throughput, low-latency serving at supercomputing scale.
• Mentor and grow engineers across the organisation.

Skills

ML project leadership

PyTorch or JAX

Inference frameworks

Python

Go or Rust

Kubernetes & Docker

Education

MS in Computer Science / ML / AI

Tools

Kubernetes

Docker

AWS

GCP

Job description

Apple is seeking a senior ML inference architect to join the Foundation Model Inference team in Paris. You will work at the intersection of research and production, delivering scalable, secure inference systems for billions of interactions across Apple services.

You will partner with research and external partners to bring cutting-edge architectures to planetary-scale deployment, shaping the technical direction and mentoring engineers while ensuring privacy and performance at scale.