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

What you'll do

• Deliver high-performance models using distributed inference libraries and optimize performance and reliability across the Neuron ecosystem.
• Lead architectural decisions and technical initiatives across the Neuron serving stack; mentor engineers.
• Collaborate with customers and cross-functional teams, and author technical documentation, design proposals, and architectural guidelines.

What they ask for

• 5+ years programming in a modern language such as Java, C++, or C#, including object-oriented design.
• 5+ years leading design or architecture of new and existing systems, including design patterns, reliability, and scaling.
• 5+ years across the full software development life cycle, including coding standards, reviews, source control, builds, testing, and operations.
• 5+ years of non-internship professional software development experience; experience mentoring, serving as a tech lead, or leading an engineering team.

Nice to have

• Master's degree in computer science or equivalent.
• Experience with machine learning and LLM fundamentals, including architecture, training/inference lifecycles, and model execution optimization.

Pay

193,300.00 - 261,500.00 USD annually (base salary)

Tools

AWS Neuron, Trainium, Java, C++, C#, vLLM Neuron plugin

AI focus

Enable and optimize dense and MoE LLMs for inference on Trainium accelerators; improve inference features, infrastructure, tools, automation, usability, and quality.