Software Development Manager, EC2 Nitro
Core
Lead a performance engineering group to establish EC2 as the definitive source for ML performance optimization across diverse workloads including LLMs, multimodal models, and next-generation AI applications.
Role type
Senior IC machine learning systems manager (performance engineering)
Builds
Foundational ML performance measurement infrastructure operating as reliable CI/CD systems across diverse accelerator platforms
Domain
Cloud infrastructure + machine learning systems
Deliverable
production ML models
Required skills
Engineering team management, system architecture design, multi-tier web services development, full software/hardware/networks development lifecycle knowledge, product/program management partnership
Preferred skills
Technical communication with users and senior leadership, recruiting, hiring, mentoring, and coaching software engineers
Technologies
CUDA, accelerator firmware, frameworks, serving layers, CI/CD systems, regression testing tools
Responsibilities
Lead design and delivery of ML performance measurement infrastructure, drive architectural decisions influencing future platform design, develop comprehensive regression coverage across component releases, establish mechanisms to scale performance engineering practices to emerging AI domains
Seniority
Senior, hands-on IC with management responsibilities
