Real-Time CV & ML Engineer – On-Device Multimodal AI

Apple, Inc.; Sunnyvale (CA); In loco; USD 185.000 - 325.000; Tempo pieno

Descrizione del lavoro

Apple Sunnyvale, CA is seeking an experienced software engineer in ML/AI to design and optimize real-time, on-device computer vision and multimodal perception systems for next-generation products.

You will collaborate with researchers and engineers across graphics, CV and ML to implement high-performance algorithms, integrating models with audio, image, and video modalities while focusing on efficiency on mobile and embedded platforms.

Competenze

• Bachelor's degree in a relevant field such as Computer Vision, Computer Graphics, ML, CS or Engineering.
• 5+ years of industry experience in software, ML or embedded systems.
• Strong proficiency in C++ and Objective-C/C++, writing clean, robust code.
• Experience building concurrent, real-time systems: threads and synchronization.
• Experience profiling and optimizing performance-critical code or ML on device.
• Solid math foundation in linear algebra and numerical analysis.
• Ability to tackle large problems and deliver robust solutions.

Mansioni

• Design and drive software architecture for production systems and internal tools.
• Implement and optimize performance-critical algorithms for mobile and embedded platforms.
• Integrate multimodal models with audio, image and video for on-device inference.
• Build tooling for visualization, logging, debugging and evaluation.
• Integrate real-time perception, 3D representation and animation into the end-to-end stack.

Conoscenze

C++

Obj-C/C++

Real-time systems

On-device ML inference

Performance profiling

Multimodal models

Math foundations

Problem decomposition

Cross-functional collaboration

Formazione

Bachelor's degree in Computer Vision/Graphics/ML/CS/Engineering or related fields

Strumenti

Core ML

MLX

ExecuTorch

vLLM

SGLang

Metal/CUDA/Vulkan

Descrizione del lavoro

Apple Sunnyvale, CA is seeking an experienced software engineer in ML/AI to design and optimize real-time, on-device computer vision and multimodal perception systems for next-generation products.

You will collaborate with researchers and engineers across graphics, CV and ML to implement high-performance algorithms, integrating models with audio, image, and video modalities while focusing on efficiency on mobile and embedded platforms.