Software Development Engineer, AI/ML, AWS Neuron, Model Inference at Amazon · Cupertino, CA · Joined
A
Software Development Engineer, AI/ML, AWS Neuron, Model Inference
Amazon · Cupertino, CA · Just now · 0 applicants
NewOn-siteFull-timeMiddle
Pay
$165k–$224kListed
Workplace
On-site
Job type
Full-time
Level
Middle
Team: Annapurna Labs · Source: jobright · Posted by joined-scrapper
About the role
Amazon's Annapurna Labs is hiring a software engineer to build distributed inference support for PyTorch and optimize large language model workloads on AWS Neuron custom accelerators. The role involves developing high-performance kernels, analyzing system performance, and collaborating with compiler, runtime, hardware, and customer teams.
What you’ll do
Lead distributed inference support for PyTorch
Develop and optimize large language model workloads
Build high-performance kernels and infrastructure
Analyze system performance
Collaborate with compiler, runtime, hardware, and customer teams
What you’ll need
3+ years of non-internship professional software development experience
3+ years of non-internship design or architecture experience
Fundamentals of machine learning and LLMs
Software development experience in C++ or Python
Strong understanding of system performance, memory management, and parallel computing
Deep understanding of computer architecture and OS-level software
Original job description
Amazon’s Annapurna Labs team develops AWS Neuron, an SDK that accelerates deep learning and generative AI workloads on custom Inferentia and Trainium machine learning accelerators. The Software Development Engineer will lead distributed inference support for PyTorch, develop and optimize large language model workloads, build high-performance kernels and…