AI/ML Inference Engineer for PyTorch on Trainium

Amazon Web Services (AWS); Cupertino (CA); On-site; USD 150,000 - 210,000; Full time

Job summary

Amazon Web Services (AWS) Annapurna Labs team seeks a Software Engineer II - AI/ML to design and optimize models for AWS Trainium accelerators. You will build distributed inference support for PyTorch, implement high-performance kernels, and collaborate with compiler, runtime, framework, and hardware teams.

You will work across the ML system lifecycle, profiling performance, applying optimizations, and enabling customers to run demanding workloads at scale on AWS accelerators.

Qualifications

• Strong software development in Python and system-level programming.
• Solid ML knowledge and experience.
• Experience with distributed systems and performance profiling.

Responsibilities

• Design, develop, and optimize machine learning models and frameworks for deployment on custom ML hardware accelerators.
• Participate in all stages of the ML system development lifecycle, including distributed computing-based architecture design, implementation, performance profiling, hardware-specific optimizations, testing, and production deployment.
• Build infrastructure to systematically analyze and onboard multiple models with diverse architectures.

Skills

Python

System-level programming

ML knowledge

Distributed systems

Performance profiling

Job description

Amazon Web Services (AWS) Annapurna Labs team seeks a Software Engineer II - AI/ML to design and optimize models for AWS Trainium accelerators. You will build distributed inference support for PyTorch, implement high-performance kernels, and collaborate with compiler, runtime, framework, and hardware teams.

You will work across the ML system lifecycle, profiling performance, applying optimizations, and enabling customers to run demanding workloads at scale on AWS accelerators.