Software Development Engineer , AWS Agentic AI Foundations

Amazon; Bellevue (WA); On-site; USD 180,000 - 240,000; Full time

Job summary

Amazon Inc. is seeking an engineer to build and enhance Bedrock AgentCore services. You will design core runtime infrastructure, eliminate Docker complexity, and optimize latency across Lambda Sandbox and other compute platforms.

You will mentor engineers and contribute to security and identity strategy in a fast-moving AWS AI context. Join a team focused on scalable, fault-tolerant services with broad impact across the business, contributing to strategic technical projects and driving

Responsibilities

• Design and implement core runtime infrastructure components including control plane APIs, data plane execution environments, and deployment orchestration systems
• Build managed runtime capabilities that eliminate Docker complexity and enable rapid iteration for developers (ZIP-based deployments, dependency management, cold start optimization)
• Optimize agent invocation latency, cold start performance, and resource utilization across Lambda Sandbox, Snapstart, and custom compute platforms
• Develop monitoring, observability, and operational tooling to ensure production reliability and enable rapid incident response
• Collaborate with AWS Lambda, Bedrock, and open-source framework teams to integrate and optimize agent runtime capabilities
• Contribute to technical strategy and architecture decisions for session management, identity/permissions, cross-account access, and security integrations
• Mentor junior engineers and drive engineering excellence through code reviews, design reviews, and operational best practices

Job description

In this role, you will build new or enhance existing Bedrock AgentCore services that are going to be trend setting in the Agentic AI field. This is an area that requires solving the hardest engineering challenges to enable machine learning powered solutions for our customers. As a tier one Amazon service our solutions have to be scalable, efficient, and fault tolerant. Experience with machine learning systems is preferred, but not required. You will deliver some of our most strategic technical projects, deliver large scalable systems, design new software systems at the cutting edge of distributed database technology and have a significant bottom-line impact on our business and competitive position. In addition to delivering critical software, you will draw from a deep and broad technical expertise to mentor engineers and provide leadership on complex technical issues. This position within the AWS AI team presents a unique and rare opportunity to get in on the ground floor within a fast growing business and help shape the technology, product and the business. A successful candidate will bring deep technical and software expertise, desire to have an industry wide impact and ability to work within a fast moving, startup environment in a large company to rapidly deliver services that have a broad business impact.

Key job responsibilities

• Design and implement core runtime infrastructure components including control plane APIs, data plane execution environments, and deployment orchestration systems
• Build managed runtime capabilities that eliminate Docker complexity and enable rapid iteration for developers (ZIP-based deployments, dependency management, cold start optimization)
• Optimize agent invocation latency, cold start performance, and resource utilization across Lambda Sandbox, Snapstart, and custom compute platforms
• Develop monitoring, observability, and operational tooling to ensure production reliability and enable rapid incident response
• Collaborate with AWS Lambda, Bedrock, and open-source framework teams (LangChain, LangGraph, Strands) to integrate and optimize agent runtime capabilities
• Contribute to technical strategy and architecture decisions for session management, identity/permissions, cross-account access, and security integrations
• Mentor junior engineers and drive engineering excellence through code reviews, design reviews, and operational best practices

A day in the life

Here at AWS, we embrace our differences. We are committed to furthering our culture of inclusion. We have ten employee-led affinity groups, reaching 40,000 employees in over 190 chapters globally. We have innovative benefit offerings, and we host annual and ongoing learning experiences, including our Conversations on Race and Ethnicity (CORE) and AmazeCon (gender diversity) conferences. Amazon’s culture of inclusion is reinforced within our 14 Leadership Principles, which remind team members to seek diverse perspectives, learn and be curious, and earn trust.

About the team

Our team puts a high value on work-life harmony. It isn’t about how many hours you spend at home or at work; it’s about the flow you establish that brings energy to both parts of your life. We believe striking the right balance between your personal and professional life is critical to life-long happiness and fulfillment. We offer flexibility in working hours and encourage you to find your own balance between your work and personal lives.