Senior Software Dev Engineer, EC2 Nitro

Job description

Join the EC2 Nitro Machine Learning Systems team to revolutionize supercomputing in the cloud. We're seeking an experienced Software Development Engineer to build and optimize infrastructure powering the most computationally intensive AI/ML workloads. In this role, you'll establish EC2 as the definitive source for best-known-configurations across diverse ML applications while influencing future accelerated platform designs. You'll bring deep expertise in ML systems performance, working across the full stack from low-level hardware optimization to high-level frameworks. This position offers unique opportunities to translate state of the art ML research into practical platform improvements, build foundational measurement infrastructure, and directly support customers with performance challenges. If you're passionate about solving complex performance optimization problems at massive scale while directly influencing product strategy, this role provides the perfect opportunity to make a significant impact. Key job responsibilities - Design and implement scalable performance measurement infrastructure that serves as the foundation for ML benchmarking across AWS, incorporating critical metrics like tokens/second, latency, and accelerator utilization - Lead technical projects establishing EC2 as the definitive source for ML performance best practices across diverse applications including LLMs, multimodal systems, and emerging model architectures - Develop and maintain comprehensive regression testing systems that validate performance across major…