Sr Site Reliability Engineer, AI Platform Inference

Adobe is seeking an outstanding Site Reliability Engineer for their AI Inference Platform, Adobe Firefly. As part of a team of Site Reliability Engineers, you'll work closely with Engineering teams to build, scale, and secure the AI Platform. This role enables Firefly product teams to easily manage and deploy Machine Learning capabilities used by Adobe client applications.

The platform will support thousands of models from Adobe Research and other App Teams, offering ML model serving at scale, with high-cost efficiency, across multiple cloud platforms. You'll be responsible for ensuring high uptime and quality of service for Adobe's customers through operational excellence.

Key responsibilities include:

• Identifying and implementing solutions to increase reliability, scalability, security, and efficiency
• Defining and measuring service level objectives (SLOs) and indicators (SLIs)
• Supporting and maintaining globally distributed, multi-cloud environments
• Automating common tasks at scale to streamline operations
• Improving service resiliency through techniques like chaos engineering and performance testing
• Coordinating with other Adobe teams and service providers to innovate on Generative AI as a Service

The ideal candidate will have a strong background in distributed systems, containerization (especially Kubernetes), and cloud technologies. They should be proficient in programming (Python or Go preferred) and have experience with infrastructure management tools, observability solutions, and AI/ML frameworks.

This role offers the opportunity to work on cutting-edge AI technologies and shape the future of Adobe's AI platform. The compensation range for this position is $154,000 - $278,800 annually, depending on qualifications and location.