Software Development Engineer - AI/ML, AWS Neuron, Multimodal Inference

Amazon

Seattle, WA, US
143,700.00 - 194,400.00 usd annually py
On-site
Python programming
System level programming
Pytorch or jax frameworks
This role involves architecting and implementing business-critical features for distributed inference support on AWS custom ML accelerators

Job Summary

  • This role involves architecting and implementing business-critical features for distributed inference support on AWS custom ML accelerators.
  • Engineers will tune large language models like Llama and DeepSeek to ensure highest performance and maximize efficiency on Trainium and Inferentia silicon.
  • The team fosters a builder's culture where experimentation is encouraged, emphasizing technical ownership and continuous learning.

Matching Summary

This role involves architecting and implementing business-critical features for distributed inference support on AWS custom ML accelerators.

Salary

143,700.00 - 194,400.00 USD annually

Skills & Requirements

Must-have

  • Python programming
  • System level programming
  • PyTorch or JAX frameworks
  • Distributed inference architecture
  • ML model performance tuning
  • AWS Inferentia and Trainium accelerators

Nice-to-have

  • Mentoring experienced engineers
  • Startup-like development environment
  • Open source ecosystem collaboration
  • Customer-facing optimization support
  • Hardware-software boundary expertise

Key Requirements

  • Strong software development using Python
  • System level programming expertise
  • Deep ML knowledge and framework experience

Work Rights

Not specified

Tailored Resume

Cover Letter