On-Device Vision ML Engineer - Multimodal Models

Apple Inc.; Sunnyvale (CA); On-site; USD 150,400 - 277,600; Full time

Benefits offered by this job

Relocation assistance

Employee stock programs

Medical and dental coverage

Tuition reimbursement

Job summary

Apple Inc. in Sunnyvale, CA, seeks a Machine Learning Systems Engineer to ship cutting-edge computer vision tech on Apple devices. You will train, evaluate, and deploy purpose-built vision models under strict on-device constraints, optimizing performance and efficiency across the ML lifecycle.

You will work on tasks ranging from on-device inference optimization to end-to-end deployment, leveraging PyTorch, C++, and Python, with a focus on multimodal models and on-device deployment scenarios.

Qualifications

• Bachelor's degree in Computer Science, ML, or related field; 3+ years of industry experience.
• Proven track record of writing production code for shipped CV/ML features.
• Strong Python/C++ programming skills with OS fundamentals.
• Hands-on experience with PyTorch and end-to-end ML lifecycle (data preprocessing, training, evaluation, edge deployment).
• Experience with SFT pipelines to adapt vision and multimodal models for on-device tasks.
• Foundational understanding of ML architectures, especially Multimodal LLMs and integration into production systems.

Responsibilities

• Develop on-device software linking multimodal AI models with production systems on Apple devices.
• Optimize on-device inference latency, memory footprint, and computational efficiency for CV/ML models.
• Benchmark and profile power consumption and thermal performance of models on Apple silicon.

Skills

Python

C++

PyTorch

SFT pipelines

Multimodal LLMs

edge deployment

Education

Bachelor's degree in Computer Science or related

Tools

Swift

CoreML

RealityKit

Job description

Apple Inc. in Sunnyvale, CA, seeks a Machine Learning Systems Engineer to ship cutting-edge computer vision tech on Apple devices. You will train, evaluate, and deploy purpose-built vision models under strict on-device constraints, optimizing performance and efficiency across the ML lifecycle.

You will work on tasks ranging from on-device inference optimization to end-to-end deployment, leveraging PyTorch, C++, and Python, with a focus on multimodal models and on-device deployment scenarios.