Senior AI/ML Software Engineer - High-Perf Inference

Amazon Web Services (AWS); Seattle (WA); On-site; USD 168,000 - 227,000; Full time

Job summary

Annapurna Labs (U.S.) Inc. in Seattle seeks a Senior Software Engineer to advance AWS Neuron’s AI accelerators. You will optimize deep learning models and work across compiler, runtime, framework, and hardware teams to push performance on Inferentia and Trainium.

You will design kernels, monitor system performance, and collaborate with customers to maximize efficiency of ML workloads on AWS accelerators.

Qualifications

• Bachelor’s degree required.
• 5+ years of professional software development experience.
• Knowledge of Python and/or C++ programming.

Responsibilities

• Lead distributed inference support for PyTorch in the Neuron SDK.
• Tune models for highest performance on Trainium/Inferentia silicon.
• Collaborate across compiler, runtime, framework, and hardware teams.
• Design and implement high-performance ML kernels and features for Neuron.

Skills

Python programming

C++ programming

Performance profiling

Parallel computing

System design leadership

Education

Master’s degree in Computer Science or equivalent

Bachelor’s degree

Tools

PyTorch

CUDA

Triton

NCCL

Job description

Annapurna Labs (U.S.) Inc. in Seattle seeks a Senior Software Engineer to advance AWS Neuron’s AI accelerators. You will optimize deep learning models and work across compiler, runtime, framework, and hardware teams to push performance on Inferentia and Trainium.

You will design kernels, monitor system performance, and collaborate with customers to maximize efficiency of ML workloads on AWS accelerators.