Senior Software Development Engineer, AWS Neuron Inference

Job Description

The role is for a software engineer in the Neuron Inference (ML Apps) team for AWS Neuron, responsible for development, enablement, and performance optimization of ML models.

Requirements

• 5+ years of non-internship professional software development experience
• Experience optimizing inference performance using PyTorch or JAX
• Strong software development using C++/Python and ML knowledge

Responsibilities

• Lead efforts building distributed inference support into Pytorch, Tensorflow using XLA and the Neuron compiler and runtime stacks
• Tune models to ensure highest performance on AWS Trainium and Inferentia silicon
• Participate in design discussions, code review, and communicate with stakeholders

Benefits

• Medical, dental, and vision coverage (multiple plan options)
• Health savings and flexible spending accounts
• 24/7 Employee Assistance Program for mental health support
• 401(k) with company match and various investment choices
• Company-paid life/AD&D and disability insurance
• Restricted stock units (RSUs) for employee ownership
• Child care and elder care referrals, adoption assistance
• Paid maternity and parental leave (including Ramp Back)
• Paid time off (PTO) and company holidays
• Employee discount on Amazon.com products
• Career Choice program (95% tuition and textbook coverage)