AI Incident-Response Software Engineer

Amazon; Arlington (VA); On-site; USD 144,000 - 194,000; Full time

Benefits offered by this job

Health insurance

401(k) matching

Paid time off

Parental leave

Job summary

Amazon is seeking an experienced Software Development Engineer to join the Reflex incident-response platform team within Amazon Robotics. The role focuses on building and operating production services and AI agents on AWS Bedrock AgentCore to triage high-severity incidents, generate real-time call intelligence, and produce structured post-incident records.

You will own features end-to-end, from discovery with Incident Managers to production deployment and operation, and you will design robust

Qualifications

• 3+ years of professional software development experience.
• 2+ years of design or architecture experience for large systems.
• 1+ years in software development engineer or related role.
• 1+ years building multi-tiered, distributed software applications.

Responsibilities

• Design, build, test, deploy, and operate production services and AI agents on AWS (Amazon Bedrock AgentCore, serverless compute, event-driven pipelines) that automate incident triage, call intelligence, communications, and post-incident documentation and reporting.
• Own features end-to-end: from discovery with Incident Managers and resolver teams, through design and deployment to production operation.
• Build foundations gating agent autonomy: LLm output evaluation, observability, and access controls aligned with Amazon standards.
• Design feedback loops capturing human reviews and incident outcomes to improve agent performance and history.
• Integrate with incident lifecycle and model consistent incident state across systems.
• Raise the bar on software quality, security, testing, and operational excellence for AI in production workflows.

Skills

Software development

Distributed systems

OO design

Programming in Java/C++/C#

Education

Bachelor's degree in CS/Engineering

Tools

AWS Bedrock AgentCore

Serverless

Job description

Amazon is seeking an experienced Software Development Engineer to join the Reflex incident-response platform team within Amazon Robotics. The role focuses on building and operating production services and AI agents on AWS Bedrock AgentCore to triage high-severity incidents, generate real-time call intelligence, and produce structured post-incident records.

You will own features end-to-end, from discovery with Incident Managers to production deployment and operation, and you will design robust