Software Development Engineer, Alexa AI

We are hiring a Software Development Engineer to design, build, and operate production systems across our core workstreams. Depending on your interests and strengths, you may contribute to:

Agent communication platform - Design and implement the SDK and communication framework that defines how external AI agents interact with Alexa"s AI runtime. Build protocol definitions, lifecycle management, and the partner onboarding tooling that makes agent integration self-service.

Intelligent request routing - Implement surface-aware and context-aware routing logic so that Alexa"s AI runtime routes requests correctly based on device type, modality, and customer context - with proper failure isolation between surfaces.

Unified agent ingress and event delivery - Build production-grade APIs and event bus infrastructure that serve as the single ingress point for all AI agent requests and enable mid-execution event delivery for proactive and autonomous agent patterns.

Key job responsibilities

• Design, implement, and operate distributed systems that power Alexa"s AI runtime at scale, including response generation, agent communication, and AI service infrastructure
• Contribute to the design and implementation of agent platform primitives: SDKs, agent registries, and communication frameworks used by multiple partner teams
• Build and maintain production-grade services with strong operational health - monitoring, alerting, runbooks, and automated remediation
• Collaborate with partner teams across the organization to define API contracts, align on system architecture, and unblock cross-team dependencies
• Participate in on-call rotations and contribute to operational excellence, including error rate reduction, incident response, and runbook automation
• Drive improvements in developer velocity: local development environments, integration test harnesses, and CI/CD tooling
• Mentor junior engineers and contribute to team engineering standards, design review culture, and code quality

About the team

Our team sits at the heart of Alexa"s AI runtime. We own the systems that transform large language model outputs into real-time, multi-modal responses delivered to millions of customers - and we build the agentic platform infrastructure that enables every Alexa AI initiative to communicate naturally and reliably at scale.

We operate at the critical interface between the AI reasoning and orchestration layer and the response delivery layer. Our work spans service decomposition and decoupling, streaming response generation, agent communication frameworks, and the SDKs and APIs that let partner teams self-serve on our infrastructure without requiring engineering involvement from our team.

We are a high-ownership, high-autonomy team. If you want to build infrastructure that other teams" products and agents run on - rather than individual features - this is the right place.