Software Development Engineer, Infrastructure Reliability Engineering
Core
Design and ship production software and AI agents on Amazon Bedrock AgentCore to automate incident triage, call intelligence, and post-incident documentation for Amazon's fulfillment network.
Role type
Senior IC software development engineer (infrastructure reliability & AI agents)
Builds
Production services and AI agents for incident response automation
Domain
Cloud infrastructure, incident management, AI/LLM integration
Deliverable
production ML models | product features
Required skills
Distributed systems design, serverless compute, event-driven pipelines, LLM output evaluation, observability, identity and access controls, C#/C++/Java/Perl, Object Oriented Design
Preferred skills
Full SDLC ownership, Machine Learning fundamentals, transformer architecture, training/inference lifecycles
Technologies
AWS, Amazon Bedrock AgentCore, serverless compute, event-driven pipelines
Responsibilities
Design, build, test, deploy, and operate production services and AI agents; Own features end-to-end from discovery to production operation; Build foundations for agent autonomy including evaluation and alerting; Design feedback loops for agent learning; Integrate with incident lifecycle systems; Raise software quality and operational excellence for AI systems
Seniority
Senior, hands-on IC