Amazon Sr Machine Learning Engineer Annapurna ML 

United States, California, Cupertino 

219533090

Key job responsibilities
In this customer-facing role, you will be responsible for helping our most strategic customers port their models to the AWS Trainium & Inferentia platforms by delivering high-quality code and customizations to make the models functional and performant. You will use and provide feedback to the various Neuron SDK libraries and help prototype and develop new features based on the latest research findings and customer requests.A day in the life
You will be required to assist our most strategic customers in porting their models to AWS Trainium and Inferentia.You will work directly with customer data scientists and ML engineering teams and write code to have the models be performant on AWS purpose-built silicon solutions. It may require low-level coding in C++ and writing custom kernels to get the best performance possible.You will also be responsible for porting the latest open-source models to AWS Trainium/Inferentia. You will also contribute to open-source projects to help add support for AWS Trainium/Inferentia in popular projects.It will require a close collaboration with the Neuron engineering team to help drive the Neuron product roadmap and give feedback on improving product quality.

- 5+ years of non-internship professional software development experience
- 5+ years of programming using a modern programming language such as Java, C++, or C#, including object-oriented design experience
- 5+ years of leading design or architecture (design patterns, reliability and scaling) of new and existing systems experience
- 5+ years of full software development life cycle, including coding standards, code reviews, source control management, build processes, testing, and operations experience
- Experience as a mentor, tech lead or leading an engineering team
- 3+ years of experience writing code to train and/or deploy deep learning models in PyTorch

- Bachelor's degree in computer science or equivalent
- Experience deploying Generative AI applications with large language or vision models into production.