Lead Software Engineer, AI/ML Model Inference

In this pivotal role, I will lead efforts to develop distributed inference support for PyTorch within the Neuron SDK. I will optimize these models to ensure optimal performance and maximize their efficiency on AWS Trainium and Inferentia silicon and servers. My responsibilities include: - Designing, developing, and fine-tuning machine learning models and frameworks for deployment on custom ML hardware accelerators - Participating in all phases of the ML system development lifecycle, including architecture design, implementation, performance profiling, hardware-specific optimizations, testing, and production deployment - Creating infrastructure for systematic analysis and onboarding of various models with diverse architectures - Designing and implementing high-performance kernels and features for ML operations, leveraging the Neuron architecture and programming models - Analyzing and optimizing system-level performance across multiple generations of Neuron hardware - Conducting detailed performance analysis using profiling tools to identify and address bottlenecks - Implementing optimizations such as fusion, sharding, tiling, and scheduling - Conducting comprehensive testing, including unit and end-to-end testing with continuous deployment through pipelines - Collaborating directly with customers to enable and optimize their ML models on AWS accelerators - Innovating optimization techniques in collaboration with cross-functional teams