Amazon
Software Development Engineer, AI/ML, AWS Neuron, Model Inference
$165K–$224K
Cupertino, CA · Full-time · Posted Sep 22, 2026
- Experience
- 3+ years of non-internship professional software development experience; 3+ years of non-internship design or architecture experience.
- Education
- Bachelor's degree in computer science or equivalent.
About the job
Develop distributed inference support and optimize large language models on AWS Trainium and Inferentia accelerators through system, framework, and kernel-level engineering.
What you'll do
- Build and tune distributed inference solutions and high-performance ML kernels for Neuron.
- Profile and optimize model and system performance, including memory use, latency, and throughput.
- Collaborate across teams and with customers to enable and optimize models on AWS accelerators.
What they ask for
- Bachelor's degree in computer science or equivalent.
- 3+ years of non-internship professional software development experience and 3+ years of non-internship design or architecture experience.
- Fundamentals of machine learning and LLMs, including model execution optimization experience.
- Software development experience in at least one of C++ or Python; strong system performance, memory management, parallel computing, and debugging/profiling skills.
Nice to have
- Master's degree or Ph.D. in Computer Science or equivalent.
- Familiarity with PyTorch, JIT compilation, AOT tracing, CUDA or equivalent kernels, Triton-like tile semantics, or production inference platforms.
Pay
165,200.00 - 223,600.00 USD annually (base salary)
Tools
AWS Neuron, Trainium, Inferentia, C++, Python, PyTorch, JAX, vLLM
AI focus
Develop and optimize distributed inference for LLMs and other ML models on custom AWS accelerators, including model enablement, kernel optimization, and performance tuning.
Model-written summary · the original posting is authoritative