Senior Software Development Engineer - Ai/ml, Aws Neuron, Multimodal Inference

Amazon

United States
On-site
Aws neuron sdk
Pytorch and jax integration
Ml compiler and runtime
Amazon's Annapurna Labs team is seeking a Senior Software Development Engineer specialized in AI/ML and AWS Neuron to optimize deep learning and GenAI workloads on custom ML accelerators. The role involves collaborating across various technology layers while fostering a culture of innovation and continuous learning

Job Summary

  • The AWS Neuron SDK is the backbone for accelerating deep learning and GenAI workloads on Amazon's Inferentia and Trainium ML accelerators.
  • This role offers a unique opportunity to work at the intersection of machine learning, high-performance computing, and distributed architectures, where you'll help shape the future of AI acceleration technology.
  • The Inference Enablement and Acceleration team fosters a builder’s culture where experimentation is encouraged, and impact is measurable.

Matching Summary

Match Score: 85

Amazon's Annapurna Labs team is seeking a Senior Software Development Engineer specialized in AI/ML and AWS Neuron to optimize deep learning and GenAI workloads on custom ML accelerators. The role involves collaborating across various technology layers while fostering a culture of innovation and continuous learning.

Skills & Requirements

Must-have

  • AWS Neuron SDK
  • PyTorch and JAX integration
  • ML compiler and runtime
  • high-performance kernels
  • system-level optimizations
  • Python and System level programming

Nice-to-have

  • customer model enablement
  • open source collaboration
  • startup-like development environment
  • knowledge-sharing and mentorship

Key Requirements

  • Experience optimizing inference performance for latency and throughput
  • Experience with large scale LLM families
  • Experience with distributed inference solutions

Work Rights

Not specified

Tailored Resume

Cover Letter