Amazon
Software Development Engineer – AI/ML Networking Disaggregated Inference, Annapurna Labs , Elastic Collectives
$165K–$224K
Cupertino, CA · Full-time · Posted Oct 1, 2026
- Experience
- 3+ years of non-internship professional software development; 2+ years of non-internship systems design or architecture experience. Preferred: 3+ years of full software development life cycle experience.
- Education
- Preferred: Bachelor's degree in computer science or equivalent.
About the job
Build and optimize high-speed networking and data-transfer software for disaggregated LLM inference across accelerators, servers, and memory.
What you'll do
- Develop and optimize software that moves KV cache and activations across hardware over AWS’s network fabric.
- Profile workloads and improve performance toward hardware limits.
- Work across networking and inference frameworks to deliver features for large production AI clusters.
What they ask for
- 3+ years of non-internship professional software development experience.
- 2+ years of non-internship experience in design or architecture of new and existing systems.
- Experience programming with at least one software programming language.
- Experience with C/C++.
Nice to have
- 3+ years of full software development life cycle experience.
- Bachelor's degree in computer science or equivalent.
Pay
165,200.00 - 223,600.00 USD annually (base salary)
Tools
C/C++, Linux, RDMA, InfiniBand, libfabric, UCX, NCCL, MPI
AI focus
Build networking and data-movement components for disaggregated LLM inference, including transferring KV cache and activations between prefill and decode pools.
Model-written summary · the original posting is authoritative