On-Device ML Engineer — Compiler & Inference Platform

MaziCTools; United States; Remote; USD 143,000 - 264,000; Full time

Benefits offered by this job

Stock programs

Discretionary bonuses

Relocation assistance

Job summary

Apple, located in Cupertino, seeks an experienced ML Engineer to build features for on-device inference and optimize compiler/tooling for ML workloads. This role focuses on delivering high-performance, low-latency ML solutions for mobile and embedded devices.

The candidate will convert models to target devices, write tests, and collaborate with HW/SW teams. Strong C/C++, Python skills and ML framework familiarity are essential for success.

Qualifications

• Bachelor's/Master's/PhD in CS or related field.
• At least 4 years in ML Engineering, System Software Engineering, or related.
• Strong proficiency in C/C++ and Python.
• Familiarity with ML fundamentals and ML frameworks.

Responsibilities

• Build features for on-device inference stack to support accuracy-preserving techniques.
• Develop ML compilers, runtimes, execution kernels, and debugging/tooling for ML models.

Skills

C/C++

Python

ML fundamentals

ML frameworks

Communication skills

Swift

On-device ML

Education

BS/MS/PhD in Computer Science or related field

Tools

PyTorch

JAX

MLIR/LLVM

Job description

Apple, located in Cupertino, seeks an experienced ML Engineer to build features for on-device inference and optimize compiler/tooling for ML workloads. This role focuses on delivering high-performance, low-latency ML solutions for mobile and embedded devices.

The candidate will convert models to target devices, write tests, and collaborate with HW/SW teams. Strong C/C++, Python skills and ML framework familiarity are essential for success.