About The Position

At Apple, we’re on the cutting edge of delivering transformative experiences. If you are passionate about pushing the limits of CV/ML and hardware acceleration, then we want you to join our team. We balance research and product to deliver Apple quality, state-of-the-art experiences, innovating through the full stack, and partnering with HW, SW and Algorithm teams to deliver optimized solutions that brings our vision to life. We're looking for highly self-motivated and hard-working individual with expertise in optimizing machine learning and computer vision algorithms that run on ANE, GPU and CPU to join our team to deliver new technologies and experiences for Apple’s current and next generation products. Are your ready to be apart of the next big thing at Apple? DESCRIPTION Work on 3D algorithms implementation and performance optimization for Apple platforms. Analyze ML network bottleneck in the mainstream neural processor/GPU/CPU. Collaborate with ML network compiler team and hardware architecture team for both short term on-device ML model optimization and long term hardware design strategy. Translate research ideas into production-quality systems and integrations. Mentor and guide emerging and mid-level engineers, sharing your expertise to foster their growth in system software technologies and ensuring high standards of code quality, innovation, and efficiency. Cultivate a culture of learning and collaboration, encouraging innovation, and supporting engineers in their development, with the potential to expand your influence across the organization.

Requirements

  • BS and a minimum of 10 years relevant industry experience
  • Proven expertise in software design and architecture, including deep experience with full-stack software design, implementation and optimization.
  • Understand software and hardware interfaces.
  • High level proficiently in C or C++ and experience working with large, complex software systems and demonstrated ability to ship high-quality production software.

Nice To Haves

  • Master’s or PhD degree in Computer Science, Computer Engineering, or a related field.
  • Strong communication skills and ability to collaborate effectively across teams and functions.
  • Solid knowledge on computer architecture, neural processor and program optimization.
  • Rich experience with popular CNN, Transformer, and Diffusion networks and their energy-efficient variants for mobile and embedded vision applications.
  • Familiar with popular ML toolboxes (PyTorch, TensorFlow etc.) and their built in techniques for network deployment (TensorRT etc.)
  • Familiar with ML network optimization techniques, such as quantization, pruning, distillation, low-rank factorization and compression methods.
  • familiar with Apple ML stack (ANE, CoreML, MPS/Metal)
  • familiar with 3D computer vision, multi-view geometry, SfM etc.

Responsibilities

  • Work on 3D algorithms implementation and performance optimization for Apple platforms.
  • Analyze ML network bottleneck in the mainstream neural processor/GPU/CPU.
  • Collaborate with ML network compiler team and hardware architecture team for both short term on-device ML model optimization and long term hardware design strategy.
  • Translate research ideas into production-quality systems and integrations.
  • Mentor and guide emerging and mid-level engineers, sharing your expertise to foster their growth in system software technologies and ensuring high standards of code quality, innovation, and efficiency.
  • Cultivate a culture of learning and collaboration, encouraging innovation, and supporting engineers in their development, with the potential to expand your influence across the organization.
© 2024 Teal Labs, Inc
Privacy PolicyTerms of Service