CV & ML Engineer

Apple, Inc.; United States; On-site; USD 150,000 - 230,000; Full time

Job summary

Apple Inc. Video Computer Vision team seeks a software engineer to design and optimize real-time on-device ML systems for Apple products. You will collaborate with graphics, CV, and ML experts to deploy robust solutions across devices.

You will work on multimodal perception, 3D representations, and animation pipelines, focusing on performance, tooling, and maintainability within a large production codebase. A strong background in C++/Objective-C++ and low-level optimization is required.

Qualifications

• Requires degree in CS/Engineering and 3+ years of industry experience.
• Strong proficiency in C++/Objective-C/C++, with on-device inference experience.
• Experience building concurrent, real-time systems and profiling performance.
• Familiarity with diffusion transformers and multimodal data is a plus.
• Ability to design robust APIs for complex architectures.

Responsibilities

• 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 modalities for efficient on-device inference
• Build tooling for visualization, logging, debugging and evaluation
• Integrate real-time perception, 3D representation and animation systems into a broader end-to-end software stack
• Develop and review user-facing APIs for complex systems

Skills

C++

Objective-C/C++

On-device ML

Real-time systems

Multimodal ML

GPU/accelerator programming

Performance optimization

Math foundations

API design

Low-level optimization

Education

Bachelor's degree in Computer Science/Engineering

MS/PhD with industry experience

Tools

Core ML

ML frameworks (MLX, ExecuTorch)

Metal

CUDA

Vulkan

LLM inference systems (vLLM, SGLang)

Job description

The Video Computer Vision organization is working on exciting technologies for future Apple products. Our team delivers computer vision and machine learning algorithms that power many Apple technologies like human understanding and human intelligence algorithms with applications for digital humans, health and AI. In this role, you will work closely with our team of experts in computer graphics, computer vision and machine learning to design and build solutions to previously unsolved challenges for Apple products and bring high impact to millions of users. You will work closely with Multimodal GenAI researchers and engineers to develop world-class audio-video perception and representation algorithms. The role focuses on building, integrating and maintaining complex real-time systems within a large production software stack. Deep understanding of machine learning inference, on-device performance optimization and low-level systems programming is highly desirable. As a member of a fast-paced team, you have the unique and rewarding opportunity to shape upcoming products that will delight and inspire millions of people every day.

The ideal candidate should possess these qualities:

• Be highly-motivated and take initiative to achieve goals, while delivering on schedule.
• Has a sense of curiosity and willingness to learn new things in order to improve the quality of their solutions.
• Works well in a collaborative setting

• Design and drive software architecture for both production systems and internal tools
• Implement and optimize performance-critical algorithms for mobile and embedded platforms
• Integrate multimodal models with audio, image and video modalities for efficient on-device inference
• Build tooling for visualization, logging, debugging and evaluation
• Integrate real-time perception, 3D representation and animation systems into a broader end-to-end software stack
• Bachelor's degree in Computer Vision, Computer Graphics, Machine Learning, Computer Science, Computer Engineering or related fields.
• 3+ years of relevant industry experience.
• Strong proficiency in C++ and Objective-C/C++, writing clean and well-structured code.
• Experience building concurrent, real-time systems: threads, synchronization and asynchronous processing.
• Experience profiling and optimizing performance-critical code or ML inference on device.
• Solid mathematical foundation in linear algebra and numerical analysis.
• Experience breaking down large problems and delivering robust solutions.
• Experience developing user-facing APIs for complex systems.
• Curiosity about new technologies and flexibility to work across different layers of the software stack.
• MS/PhD with relevant industry experience.
• Experience with audio, computer vision, 3D graphics and animation algorithms.
• Low-level optimization experience, such as deploying algorithms to GPUs or other hardware accelerators, or GPU programming with Metal, Vulkan or CUDA.
• Understanding of SW/HW parallelism, threads, processes and asynchronous processing.
• Experience with on-device inference frameworks such as Core ML, MLX or ExecuTorch, or with LLM inference systems such as vLLM or SGLang.
• Knowledge of diffusion transformer models especially in context of on-device inference.
• Experience developing and integrating agentic workflow frameworks with tool calling components.
• Hands-on experience using AI coding assistants such as Claude Code or Codex, including the judgment to review and validate generated code.