Amazon Machine Learning Engineer AGI - Web & Knowledge Services 

United States, California, Sunnyvale 

779036805

In this role, you will work alongside renowned researchers and engineers to enable our customers to seamlessly interact with content. You will design, develop, and deploy scalable and efficient machine learning models and systems to power these transformative applications. The scope of these efforts includes defining public APIs, performance tuning and analysis, crafting and implementing compiler and optimization techniques for neural networks, and other general software engineering work.
Key job responsibilities
* Design and build scalable infrastructure that enables training, evaluating and deploying machine learning models
* Design and develop tools for monitoring the performance of machine learning models at scale
* Design and develop lineage and artifact tracking infrastructure
* Design and develop reproducible ML Pipelines orchestrating various components for ML models.
* Optimize model performance, robustness, and efficiency through techniques like model compression, knowledge distillation, and hardware acceleration
* Embrace and champion engineering best practices within your group and beyond
* Produce clean, high-quality code, tests, and written documentation
* Mentor and guide junior engineers, share knowledge, and contribute to an innovative, collaborative culture

- 3+ years of non-internship professional software development experience
- 2+ years of non-internship design or architecture (design patterns, reliability and scaling) of new and existing systems experience
- Experience programming with at least one software programming language

- 3+ years of full software development life cycle, including coding standards, code reviews, source control management, build processes, testing, and operations experience
- Bachelor's degree in computer science or equivalent
- Experience working with ML frameworks such as Pytorch, TensorRT, Onnx, AWS Neuron and accelerating deep learning models for GPU/CPU/Inferentia architectures.