Come help us build AWS DevOps Agent, a frontier agent that investigates operational incidents and helps resolve them, so on-call engineers can get back to building.
Operations is being reinvented, and we want engineers who will help lead that change. You'll work with a talented, collaborative team and build at the intersection of AI and software engineering. We design agentic systems that fit into a customer's existing environment and take on their operational toil. When an incident hits a live system, our agents help engineers diagnose and resolve it quickly. Then we learn from each incident and feed those lessons back into the system, so every one drives lasting, systemic improvement.
Your impact will be immediate and visible. You'll ship features that directly change how customers operate applications on AWS and other clouds. You'll also help shape how our own team operates, raising the bar on our engineering practices, operational excellence, and on-call experience.
Key job responsibilities
You'll shape the technical direction and architecture of the DevOps Agent service. You'll work directly with customers to uncover real-world development challenges and translate them into product capabilities—staying true to Amazon's customer-obsessed approach. You'll use DevOps Agent in your day to day work to identify and then drive improvements across the entirety of our service.
Your responsibilities span the full lifecycle: from architectural decisions to hands-on development. You'll help define all aspects of our service, for example how our agent investigates and resolves incidents, how it learns from each investigation and gets better, and how it integrates with existing customer systems
You'll balance innovation with operational excellence, making technical choices that enable development velocity while meeting AWS's standards for scale and security.
