SDM - ML Inference Experience, SageMaker Inference

DescriptionJob summaryThe team that we are hiring for belongs to the larger SageMaker service (https://aws.amazon.com/sagemaker/). We at SageMaker are blazing the trail in the ML platform domain. Within the larger SageMaker team, Inference suite of services offer rich inference modes to perform low latency, high throughput and high availability inference capabilities. In addition to taking care of core inference and related abstractions, we also provide rich Inference Experience through ML value added capabilities like Model Monitoring. Model Monitoring capability enables customers to monitor the performance of the deployed model and alert practitioners when the model starts decaying or the input data distribution changes. We are set out to expand the portfolio of such ML value added capabilities in the Inference domain to further enhance the overall Inference Experience to cover complex use-cases and data types. We have some exciting ongoing initiatives and more planned for 2022 and beyond. Watch out for an update in this space, as we are launching some new capabilities in the upcoming 2021 reInvent. 2022 and beyond is both exciting and promising.About the role - We need a strong, ML savvy engineering leader with experience building and operating large scale distributed systems, to lead the overall Inference Experience space. Your goal is to improve the overall usability of the platform, add ML value added capabilities and aid customers with performance, latency, throughput, correctness and overall cost management of model deployment and inference. You will be the single threaded leader who owns the strategy and roadmap of Inference Experience. You will be the leader of leaders and will manage a strong team of engineers directly/indirectly. In addition to the backend capabilities, you will also own the frontend experience for the Inference domain. You will be working in the company of some of the brightest minds of the industry to redefine the way ML and especially Inference is done on cloud.Key job responsibilities· Lead and grow teams of great people· Create, enhance, and run wonderful services that millions of people use to make their lives easier· Define and manage the roadmap strategy for your services - including brand new ones - in consultation with our product managers· Collaborate with and learn from world leaders in distributed systems development and operationsAbout the teamSageMaker Inference is a fast-paced team and we focus on building right customer experience. We operate in highly ambiguous environment with no set patterns to follow and we are constantly innovating on behalf of customers. We have the mission to deliver best Inference Experience on the cloud!BASIC QUALIFICATIONS· 7+ years of experience working directly within engineering teams· Experience partnering with product OR program management teams· 3+ years of people management experience, managing engineers· 3+ years of experience architecting and designing (architecture, design patterns, reliability and scaling) of new and current systemsPREFERRED QUALIFICATIONSPREFERRED QUALIFICATIONS· Experience with large scale distributed systems· Experience building and operating mission critical, highly available (24x7) systems· Experience with Machine Learning· Experience building tools for data scientists or developers· Experience in preparing quality metrics and effectively engaging with stakeholders to set and drive quality goalsAmazon is committed to a diverse and inclusive workplace. Amazon is an equal opportunity employer and does not discriminate on the basis of race, national origin, gender, gender identity, sexual orientation, protected veteran status, disability, age, or other legally protected status. For individuals with disabilities who would like to request an accommodation, please visit https://www.amazon.jobs/en/disability/us.