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.
Basic Qualifications
- 3+ years of non-internship professional software development experience
- 2+ years of non-internship design or architecture (design patterns, reliability and scaling) of new and existing systems experience
- Bachelor's degree or foreign equivalent in Computer Science, Engineering, Mathematics, or a related field
- Experience programming with at least one software programming language
Preferred Qualifications
- Master's degree or equivalent
- Experience designing, building, operating, and managing large-scale distributed systems or web services
- Experience in machine learning, data mining, information retrieval, statistics or natural language processing, or experience in developing and deploying LLMs in production on GPUs, Neuron, TPU or other AI acceleration hardware
- Experience or certifications in API design, cloud architecture/deployment, service-oriented architecture, mobile development, performance optimization, databases design and related fields
- Experience with streaming systems, real-time data pipelines, or event-driven architectures (e.g., Kinesis, EventBridge, Kafka, or equivalent)
- Familiarity with agentic frameworks, agent communication protocols, or multi-agent orchestration systems
- Strong operational instincts — experience owning production systems on-call, reducing error rates, and building runbook automation
Amazon is an equal opportunity employer and does not discriminate on the basis of protected veteran status, disability, or other legally protected status.
Our inclusive culture empowers Amazonians to deliver the best results for our customers. If you have a disability and need a workplace accommodation or adjustment during the application and hiring process, including support for the interview or onboarding process, please visit https://amazon.jobs/content/en/how-we-hire/accommodations for more information. If the country/region you’re applying in isn’t listed, please contact your Recruiting Partner.
The base salary range for this position is listed below. Your Amazon package will include sign-on payments and restricted stock units (RSUs). Final compensation will be determined based on factors including experience, qualifications, and location. Amazon also offers comprehensive benefits including health insurance (medical, dental, vision, prescription, Basic Life & AD&D insurance and option for Supplemental life plans, EAP, Mental Health Support, Medical Advice Line, Flexible Spending Accounts, Adoption and Surrogacy Reimbursement coverage), 401(k) matching, paid time off, and parental leave. Learn more about our benefits at https://amazon.jobs/en/benefits.
USA, WA, Bellevue - 143,700.00 - 194,400.00 USD annually