Principal Software Engineer, Distributed Coding Agents, Kiro

Principal Engineers provide technical leadership at Amazon. They help establish technical standards and drive Amazon"s overall technical architecture, engineering practices, and engineering methodologies. They work on our hardest problems, building high-quality, architecturally sound systems that are aligned with our business needs. They think globally when building systems, ensuring Amazon builds high-performing, scalable systems that fit well together. Principal Engineers are pragmatic visionaries who can translate business needs into workable technology solutions. Their expertise is deep and broad. They are hands on, producing both detailed technical work and high-level architectural designs.

On the Kiro team, this means leading the technical direction for agentic AI systems that power Kiro, Amazon"s GenAI coding assistant. You"ll work at the intersection of distributed systems and AI agent design, defining how multi-agent workflows are built, orchestrated, and scaled.

Key job responsibilities

• Designing and evolving the systems that orchestrate multi-step agentic workflows across multiple LLM models with low latency and high reliability
• Driving integration strategy across model providers and internal science teams as the model landscape rapidly evolves
• Defining agent orchestration architecture - designing patterns for multi-agent coordination, agent swarms, and tiered agent architectures
• Building orchestration visibility systems - creating mechanisms that make agent behavior observable, debuggable, and controllable at scale
• Solving context management at scale - architecting solutions for context sharing across agent swarms and multi-agent workflows
• Owning performance and scalability for systems where latency directly impacts developer productivity
• Setting the technical direction for a team that rapidly iterates on its architecture to stay at the frontier
• Serving as the technical anchor for ambiguous, open-ended problems and influencing how agentic AI systems are built across Amazon