Software Development Engineer AI/ML, Inference Model Enablement, AWS Neuron

Role responsibilities

Onboard and optimize state-of-the-art open-source and customer LLMs for inference on AWS Trainium accelerators. Lead technical initiatives, mentor team members, and drive architectural decisions for the Neuron serving stack.

Requirements

Requires 5+ years of professional software development experience in modern languages like Java, C++, or C# with a focus on system design and architecture. Preferred candidates have a Master's degree in Computer Science and experience with ML/LLM fundamentals and optimization.

Key skills

Java, C++, C#, Object-Oriented Design, System Architecture, Machine Learning, Large Language Models, Model Optimization, Distributed Inference, Performance Tuning, System Reliability, Technical Leadership, Software Development Life Cycle, vLLM, AWS Neuron, Trainium

Keywords

AWS Neuron, Trainium, LLM, Inference, Machine Learning, MoE, vLLM, Distributed Inference, Performance Optimization, System Design, C++, Java, C#, Object-Oriented Design, Software Development Life Cycle, Cloud-scale Accelerators, Compiler, Runtime, Architecture, Scaling, Reliability, Technical Documentation, Design Patterns, Deep Learning, AI/ML