C/c++ Hardware / Software Co-design Sde, Machine Learning Acceleration Systems

Amazon Amazon · Big Tech · Austin, TX · Software Development

This role involves developing bare metal firmware for custom ASIC-based ML Accelerator chips, focusing on hardware/software co-design to enable machine learning execution. The primary focus is on the low-level software that drives the hardware for ML inference.

What you'd actually do

  1. Software / hardware architecture and co-design
  2. Bare metal C/C++ software development, testing, debug, and performance improvements
  3. Test suite and infrastructure development
  4. Developing software which can be maintained, improved upon, documented, tested, and reused
  5. Close collaboration with RTL designers, design verification engineers, other software teams and customers

Skills

Required

  • 3+ years of non-internship professional software development experience
  • 2+ years of non-internship design or architecture (design patterns, reliability and scaling) of new and existing systems experience
  • 2+ years of programming using a modern programming language such as Java, C++, or C#, including object-oriented design experience

Nice to have

  • 3+ years of full software development life cycle, including coding standards, code reviews, source control management, build processes, testing, and operations experience
  • Bachelor's degree in computer science or equivalent
  • Experience in computer architecture
  • Experience writing firmware or bare metal software using C/C++

What the JD emphasized

  • custom Amazon-designed silicon
  • custom ASIC-based ML Accelerator chips
  • bare metal firmware
  • hardware-accelerated Machine Learning systems
  • pre- through post-silicon development
  • co-develop the firmware and custom hardware
  • ML infrastructure
  • deep learning capabilities
  • bare metal software

Other signals

  • custom silicon solutions
  • ML Accelerator chips
  • bare metal firmware
  • hardware/software co-design