Senior SDE: C/C++ for HW/SW Co-Design & ML Acceleration

Amazon; Cupertino (CA); On-site; USD 193,300 - 261,500; Full time

Benefits offered by this job

Health insurance

401(k) matching

Paid time off

Parental leave

Job summary

Annapurna Labs, a AWS subsidiary, is seeking a Lead SDE C/C++ for hardware/software co-design in the ML acceleration domain in Cupertino, CA. You will develop bare metal firmware and drive neural network model execution on custom ASIC-based ML accelerators.

Join a fast-paced team blending hardware and software, collaborating with RTL and verification teams while mentoring engineers and shaping technical direction. Prior ML knowledge is not required, onboarding will cover the ML accelerator stack.

Qualifications

• 7+ years of programming with at least one software language.
• 7+ years of full SDLC experience including code reviews and builds.
• 5+ years leading design or architecture of systems.
• Experience in embedded development in C/C++.
• Experience as a mentor or tech lead.

Responsibilities

• Apply software/hardware co-design principles.
• Design, implement, test, debug embedded software and optimize performance.
• Design test suites and infrastructure.
• Own maintainable, well-documented software.
• Collaborate with RTL designers and verification engineers.
• Provide technical direction for software engineers.
• Mentor and coach other engineers.

Skills

Embedded C/C++

Leadership/Mentorship

SDLC experience

Software design/architecture

Team collaboration

Education

Bachelor's degree in Computer Science

Job description

Annapurna Labs, a AWS subsidiary, is seeking a Lead SDE C/C++ for hardware/software co-design in the ML acceleration domain in Cupertino, CA. You will develop bare metal firmware and drive neural network model execution on custom ASIC-based ML accelerators.

Join a fast-paced team blending hardware and software, collaborating with RTL and verification teams while mentoring engineers and shaping technical direction. Prior ML knowledge is not required, onboarding will cover the ML accelerator stack.